Search

[Objectives]This paper aimed to solve the problem of low target detection accuracy of apples with different ripeness under natural environment. [Methods]An improved YOLOv5s model SODSTR-YOLOv5s(YOLOv5s with small detection layer and omni-dimensional dynamic convolution and swin transformer block)was proposed for different ripeness apple detection. Firstly, the multi-scale target detection layer of YOLOv5s was improved, and the detection head of 160×160 feature map was constructed in Prediction to improve the detection accuracy of small-size apples with different ripeness. Secondly, Swin Transformer Block was integrated into the Backbone structure to strengthen the texture feature fusion of apples at the same level of ripeness, weaken the negative impact of the difference in texture feature distribution, and improve the generalization ability of the model. Finally, the Conv module of Neck structure was replaced by the dynamic convolution module ODConv, and the local feature mapping was refined to realize the full extraction of local apple fine-grained features. Experiments were carried out based on different ripeness apple data sets to verify the performance of the improved model. [Results]The precision, recall and average precision of the improved model SODSTR-YOLOv5s were 89.1%, 95.5% and 93.6%, respectively. The average precision of high, medium and low ripeness apples was 94.1%, 93.1% and 93.7%, respectively. The average detection time was 16 ms and the number of parameters was 7.34 M. Compared with the YOLOv5s model, the precision, recall and average precision of the improved model SODSTR-YOLOv5s increased by 3.8%, 5.0% and 2.9%, respectively, and the number of parameters and average detection time increased by 0.32 M and 5 ms, respectively. [Conclusions]The improved model SODSTR-YOLOv5s improved the detection ability of apples with different ripeness under natural environment. It can better meet the detection requirements of actual apple picking. [ABSTRACT FROM AUTHOR]

【Objective】By studying the hyperspectral characteristics of apple damage and establishing the best classification model of apple damaged area based on hyperspectral imaging, we can provide an important basis for realtime, rapid and accurate identification of apple damage.【Method】This paper investigates the use of hyperspectral image technology to detect mechanical damage on fruit surfaces using apple samples collected from Pinggu District, Beijing as the research object. Using the hyperspectral image (HSI) data in the range of 390-1 000 nm, the spectral response characteristics of the damaged and normal ROI areas was analysed by ratio spectroscopy, and three types of spectral indexes, namely the normalized difference spectral index (NDSI), the ratio spectral index (RSI) and the difference spectral index (DSI) were selected and constructed to better highlight the characteristics of the damaged areas..On the basis of these indexes, the spectral indexes with better ability to extract damage areas were selected, and the unsupervised data clustering algorithm of iterative self-organizing data analysis techniques algorithm (ISODATA) was used to extract apple damage areas.【Result】 The spectral reflectance changed significantly when the apple surface was damaged. After waveband optimization, it was found that the reflectance of 528 nm and 676 nm could effectively identify the abnormal areas. Based on the selected feature bands, the recognition spectral indexes for apple damage detection were constructed, including NDSI, RSI and DSI. By the pixel value analysis of the spectral index images, the damaged area features were distinguished from the normal area features in each SI enhanced image obviously. Among them, the difference between the NDSI pixel averages of the two types of image features was the largest, reaching 0.629, which indicated that the established NDSI has a strong ability to distinguish between the damaged area and normal area features. Using the unsupervised classification method ISODATA classification, it was verified that the spectral feature index has high specificity in detecting apple damage, and the accuracy rate of apple damage reached 92.50%. 【Conclusion】The results are applicable to the real-time and rapid detection of apple damage, providing a technical basis and reliable reference for the accurate management of apple production. [ABSTRACT FROM AUTHOR]

Apple pesticide residues not only compromise food safety, but also seriously endanger public health. Accurate and rapid detection of pesticide residues is an important means to ensure food safety. This paper reviewed the detection methods of pesticide residues in apple in recent years and introduced traditional detection techniques such as gas chromatography, gas chromatography-mass spectrometry, high performance liquid chromatography, and high performance liquid chromatography-mass spectrometry, as well as rapid detection techniques including surface enhanced Raman spectroscopy, near infrared spectroscopy, electrochemical method, and several new detectable techniques in the application of pesticide residues detection in apple. Also it look forward to the combination of traditional detection techniques and rapid detection techniques to solve the problem in order to provide technical support for the detection of pesticide residues in apple. [ABSTRACT FROM AUTHOR]

The cultivation of apples plays an important role in China's fruit production. Climate change has brought about more frequent and severe drought and waterlogging disasters, which have negatively impacted apple yield quantity and quality. Through the summary of previous research studies done on the impact of drought and waterlogging disasters and its effect on apple production, methods for disaster prevention and mitigation can be provided to reduce the impact of these disasters to the industry. In this paper, the methods of classification and systematic analysis combined with studying actual disaster cases were used to review the latest research into the effects of droughts and waterlogging disasters on apple production in China and identify the next steps for future research and development into this subject. The intensity and impacts of droughts and waterlogging disasters on apple production are determined by weather, regional climate, topography, soil composition, and several other factors. Adopting the morphological indicators to study these disasters, most existing research into this area only focuses on meteorological factors and rarely consider agrometeorological factors such as soil composition, current crop conditions, and more. The distribution of apple drought disasters in China decreases from north to south. The prevention measures of apple drought and waterlogging included irrigation, strengthening orchard soil management, implementing the integration of soil and fertilizer, etc. More of the current research done into this subject takes place in the Northern parts of China and often lack the necessary information to be put into use in disaster monitoring and early warning applications. In the future, research into apple droughts and waterlogging disasters should focus on increasing in orchard observation data collection, constructing a disaster risk monitoring and early warning model, and implementing the model into apple growing. [ABSTRACT FROM AUTHOR]

Three major production areas of Fuji apple, Linyi (in Shanxi province), Luochuan (in Shaanxi province) and Qixia (in Shandong province) were selected as the study region, based on 1 km gridded meteorological data, actual first flowering date data, and Chilling Hour Model (CHM) and Growing Degree Hour (GDH) data of the survey sample points in 2019-2020, the optimal chill/heat requirement at the first flowering date of apple was obtained using the gridded search method. Then, the daily air temperature characteristic values (Tmax, Tmin and Tavg) were divided into seven daily air temperature characteristic factor combinations, including single factor, double factors and triple factors, and the random forest algorithm (RF) was used to establish three regional daily chill/heat accumulation models with different daily air temperature characteristic factor combinations to select the optimal daily air temperature characteristic factor. On the basis of which, forecasting model of apple first flowering date was established based on the optimal daily air temperature characteristic factor by using RF algorithm, and the accuracy of the forecasting model was evaluated by independent actual first flowering date data. The results showed that: (1) the optimal chill/heat requirement at the first flowering date for apple in three regions were 730CH and 7350GDH in Linyi, 345CH and 4950GDH in Luochuan, and 520CH and 4450GDH in Qixia. (2) Among the seven combinations of daily air temperature characteristics, the three regional daily chill/heat accumulation models with the combination of Tmax, Tmin and Tavg had high accuracy in estimating daily chill/heat accumulation, and the RMSE between the estimated daily chill accumulation and the daily chill accumulation obtained from the CHM model was 0.97-2.50CH, and the RMSE between the estimated daily heat accumulation and the daily heat accumulation obtained from the GDH model was 1.73-15.76GDH. (3) When the daily chill/heat accumulation was estimated by forecast model of apple first flowering date, the RMSE between the estimated daily chill accumulation and the daily chill accumulation based on the CHM model ranged from 1.08 to 1.14CH, and the RMSE between the estimated daily heat accumulation and the daily heat accumulation based on the GDH model ranged from 2.03 to 3.74GDH. When the model was used to forecast first flowering date of apple, R² between the predicted and actual first flowering date was 0.92, and RMSE was 3.44d. The accuracy of the predicted first flowering date based on daily air temperature characteristic values was in overall agreement with that based on real hourly air temperature data, it indicated that the forecast model of apple flowering date established in this paper could effectively convert the input air temperature data from hourly scale to daily scale, which will have good application value and potential in the subsequent work on apple first flowering date forecasting. [ABSTRACT FROM AUTHOR]

[ Objective] This paper aimed to understand the biological information and function of the Heat shock transcription factor( Hsf) in apple. [ Method]36 Hsfs were retrieved from the apple genome GDH13 vl. l,confirmed by Pfam and NCBI Conserved Domain Database,and then,TBTools,ExPASy,MEME and other software were used to further analyze33 genes with complete Hsf domain. [ Result]The proteins encoded by these genes contained 189 - 530 amino acids, with molecular weights of 21 703. 71 - 58 972. 96, and isoelectric points of 4. 55 - 8. 58. The prediction of subcellular localization showed that MD00G1095900 and MD02G1171800 could be located in chloroplast/nucleus, MD05G1313700 could be located in nucleus/mitochondria,and other Hsf were localized in the nucleus. Chromosome mapping and synteny analysis showed that there was no tandem duplication of apple Hif genes, but there were segmental duplication in 16 pairs of 24 apple Hif genes. Under saline-alkali stress, the expression of most Hif genes were significantly down-regulated. Protein interaction network analysis showed that MD03 G1258300 interacts with heat shock protein, superoxide dismutase copper chaperone, protein phosphatase 2C, and sucrose unfermentable 1-associated protein kinase 'Y regulatory subunit. MD15G1283700 interacts with heat shock protein, IAA amino acid hydrolase and alkaline leucine zipper. [Conclusion] Hsfs of apple may play an important role in regulating the response to saline-alkali stress, which provides some theoretical reference for further study of biological functions of Hsfs in apple. [ABSTRACT FROM AUTHOR]

Eastern Gansu is the most important apple base of Gansu province, but drought, freezing damage, hail and other meteorological disasters occured frequently during growth period of apple, which could lead to loss in yield and quality. Therefore, it was necessary to evaluate the integrated risk of multiple meteorological disasters on the growth of apple. In this paper, the meteorological data of 22 counties (districts/cities) in eastern Gansu from 1965 to 2018, planting area and yield of apple from 1995 to 2018, and other socio-economic statistics data for the latest 5 years were employed.12 indices of 4 kinds were analyzed and selected, and the integrated risk index system was established using disaster risk analysis theory. The weights of risk indices were determined by the compromising method between analytic hierarchy process method and entropy-coefficient method. In addition, the risk value of each evaluated unit was calculated. Therefore, an integrated risk evaluation index model of meteorological disasters was established and the risk was zoned and evaluated with GIS technique. The studied region was divided into four-risk-grade areas according to the integrated risk value, including mild risk area, moderate risk area, severe risk area and severity risk area. The results showed that hazard of the disaster-causing-factors was the most important factor influencing the integrated risk, the vulnerability of the hazard-affected body takes the second place, while the sensitivity of disaster environment and the disaster prevention and mitigation capability play alleviative roles in the risk factors composition. The integrated risk of meteorological disasters on apple growth in eastern Gansu shows a trend of increasing from southeast to northwest. The regions with severe and severity risk were mainly distributed along the mountainous area of Guanshan, the both sides of Liupan Mountain, and the north of Longdong Loess Plateau, with the risk index value of above 0.45; the regions with the moderate risk were mainly distributed in the south-central part of Longdong, and most of the Weihe River Basin, with the value between 0.25 to 0.45; the regions with the mild risk were only scattered in a small part of the Weihe River Basin, and the southeast of Longdong, with the value of below 0.45. [ABSTRACT FROM AUTHOR]

As a new processing technology, RF heating has great potential in blanching of fruits and vegetables. Dielectric property is the main factor affecting the RF heating of fruits and vegetables. It is affected by frequency, temperature, water and other factors. According to the change of dielectric property, the blanching process of fruits and vegetables can be optimized and improved. In this paper, the dielectric properties of Fushi and Qinguan apple pulp at different temperatures (25, 40, 60, 80, 95 ℃)and different frequencies (13.56, 27.12, 40.68, 915, 2 450 MHz) are determined by using the open-ended coaxial probe technique. A RF heating system with the power of 6 kW and the frequency of 27.12 MHz is used to study the heating speed and uniformity of apple sample. Different electrode gaps (110, 120 and 130 mm) are set to heat the apple slice (20 mm × 20 mm × 50 mm). When the center temperature of the apple sample reaches 95 ℃, the heating is stopped. The temperature rise curve of apple sample from room temperature to 95 ℃ is recorded with fluorescent fiber temperature measuring system under different electrode gaps. The temperature distribution of the surface of the heated apple sample is measured by infrared thermal imager. The results show that the dielectric constant and loss factor of apple slice change significantly with temperature and frequency. At the same temperature, as the frequency (12-3000 MHz) increases, the dielectric constant decreases first and then increases and then decreases. The loss factor reduces first increases then and decreases then; at the same frequency, there is no specific law for the dielectric constant and loss factor of apple. The temperature of the apple sample rises from 25 ℃ to 95 ℃, and the temperature rise curve approximates linear growth. When the electrode gap is 110mm, the temperature rise is the fastest. When the electrode gap is 130 mm, the temperature rise is the slowest, 120 and 150 s, respectively. The heating speed increases with the decrease electrode gap. During the process of RF heating, the temperature distribution of the apple sample is centered, that is, the center temperature is high and the edge temperature is low. The maximum temperature occurs at the center point, and the maximum temperature of the lower segment equidistant from the center is greater than that of the upper segment. The present study shows the great potential of RF heating for the blanching of fruit and vegetable. Future studies should aim to determine changes in the texture and nutrient contents of fruit and vegetable during RF heating. [ABSTRACT FROM AUTHOR]

Aiming at the present situation of high labor intensity and low precision of plant spacing control in fruit tree planting, the agricultural machinery agronomic integration technology based on standardized cultivation mode was studied in this paper, and an apple planting machine for high density dwarfing orchard was designed, the key technical problems in mechanized planting of fruit seedlings, such as continuous wide and deep furrow opening, vertical planting of fruit seedlings and precise control of plant spacing, were solved. The apple planting machine for high density dwarfing orchard was powered by a tractor above 58 kW and used a rear three-point suspension operation mode. The structure mainly composed of continuous ditching device, clamping and conveying device, fixed-distance planting device, overburden pressing device and other auxiliary devices. The ditching device was powered by power-output shaft to drive opener ditching continuously. V-type double-disc opener was used, ditching blade was installed on ditch cutter supported by inclined bearings. Soil retaining plate was installed at the rear of the opener, front and side plates were used with the opener to ensure the grooving structure was stable. Bottom plate was used together with grid bar to assist positioning. By manually placing the seedlings and placing the rotes on the bottom plate, the tree trunk was placed obliquely on the grid bar lying on the conveying channel for initial positioning. After the sensor of the fixed-distance planting device installed at the rear of the frame detected the position information of the planted seedlings, the cylinder action of the clamping conveyor was started by controlling the switch. the positioning bar was opened, and the seedlings entered the clamping state, and then the seedlings were transmitted backward by the carrying belt. The carrying belt was powered by the ground wheel with the same rate, therefore, the speed of the carrying belt was the same as the machine working speed, and the seedlings were placed in the planting ditch statically with a zero speed relative to the ground, then the scraper-type cover pushed back the soil and the compaction wheel pressed the soil compactly, at the same time it pushed forward the seedlings to complete the upright planting. The fixed-distance sensor detected the seedlings just planted, the process was repeated, ensuring the distance between the adjacent 2 seedlings was equal, continuous ditching, vertical planting, backfilling and repressing were realized in one-time. By adjusting the height of the bottom plate (from 0 to 20 cm), the angle and depth for initial inclined positioning could be changed, so that the machine could work in different soils and for different varieties. The ditching depth of the machine was adjustable from 0 to 40 cm, the ditching width was 30~37 cm, and the working speed was 0.8-1.5 km/h. The results of field experiment showed that the average qualification rate for planting depth was 91.43%, the average planting qualification rate was 93.79%, and the variation coefficient of plant spacing was about 5.03%, average planting efficiency was about 720 plants per hour, which was 36 times more efficient than manual planting, the machine worked stably and the planting effect met the mechanized production requirements of modern standard orchard. [ABSTRACT FROM AUTHOR]

[Objective] Through the different data transformation of original spectral data, to analyze its correlativity between apple canopy PAR and establish the hyperspectral model of apple canopy PAR in the southern Xinjiang based on hyperspectral. the present paper aims to provide effective ways for a fast and accurate, no-damage, and wide range of timely, dynamic monitoring of vegetation PAR. [Method] Based on the different data transformation methods of the original spectral data, adapt correlation analysis and stepwise regression analysis. [Result]The canopy spectral reflectance with different transferred data has great correlations between apple canopy PAR, the correlation after differential transformation was higher than that of the original. After the accuracy evaluation, it is found in model that the original spectral data after the reciprocal first order differential transformation, the estimation model has the highest degree of fitting, and the first order differ­ential , logarithmic first order differential are following. [Conclusion ] The spectral data with different data transformation have certain correla­tion with apple canopy in Tarim Rasin, and it can use the data with differential, logarithmic differential, reciprocal differential transformation to establish estimated model of tarim basin apple canopy PAR. [ABSTRACT FROM AUTHOR]

Correctly identifying apple from image is the premise of apple harvesting robot for achiving automatic picking. On the basis of the study of this problem, this paper proposed a new apple target recognition algorithm based on significant contour. Firstly, it used the K-means unsupervised clustering algorithm to segment apple image which was divided into background and apple target area. Due to factors such as light, the apple target region after K-means segmenting contained large hole, so it introduced the ASIFT feature to match between the complete apple target image and the apple target image which included hole, and recorded the features corresponding to the hole, and filled the hole by pixels relating to those features. Then, based on the area, it detected the apple target image5 s contour by gPb contour detector to generate longer and moreobvious gray contour image. Finally, it removed much edge noise around the target through the dynamic threshold Otsu for automatic threshold processing to process the gray contour image, and achieved a complete extraction of the contour of the target by determining the continuous and significant contour. Experimental results show that, the proposed approach is more accurate and more robust, the correct recognition rate of apple target is above 98%. [ABSTRACT FROM AUTHOR]

Vision system is one of the most important parts of apple picking robot, which, to some extent, determines the quality and the speed of picking task implemented by apple picking robot. In this review, we enumerated the existing apple picking robots. Some information, such as type of visual sensors, hardware of vision system, success rate of harvesting and run time, was illustrated in details. Meanwhile, on the basis of discussing the vision system of apple picking robot, we focused on summarizing hardware structure of existing vision systems and apple image segmentation methods as well as apple recognition and localization methods applied in vision systems. The vision system of apple picking robot mainly includes machine vision system, laser vision system, three-dimensional vision system and vision system formed by machine vision and other vision system. And the machine vision system can be classified into 3 types according to the number of image sensors used, that is, monocular vision system, binocular vision system and multi vision system. The recognition and localization of apple target is the first step of the implementation of the picking task for picking robot. The currently used apple segmentation and recognition methods include threshold segmentation algorithm, chromatic aberration based algorithm, K-mean clustering algorithm, region growing algorithm, segmentation method combining 2 or more algorithms, and so on. There are 4 methods that are commonly used in the localization of apple target. They are the methods based on centroid, fitting circle, symmetry axes, and three-dimensional coordinates, respectively. In natural scene, the recognition and localization of apple target may be affected by many factors. Hence, recognition and localization of apple target under different conditions, such as color nonuniformity, different illumination, shadow on the surface, oscillation, overlapping and occlusion, was reviewed and analyzed. Among all these conditions, occlusion can be regarded as the most serious factor. The condition of occlusion can be roughly divided into 4 kinds, i.e. apple target blocked by other apple, by branches, by leaves and by branches, leaves and other apple simultaneously. As for apple targets blocked by branches, one apple may be separated by branches, thus causing that an apple may be recognized as several apples. For the apple targets blocked by leaves, the symmetry of apple can be utilized to localize apple targets. The apple targets blocked by other apple can be considered as overlapping. There are overlapped apples with series connection, parallel connection, and blend connection. Because of the complexity of overlapping, the recognition and localization of apple targets blocked by other apple target is a little more difficult. In addition, the detection of obstacles like tree trunk and branches in apple orchard is important for apple picking robots to avoid obstacles, and thus obstacles detection methods were summarized in this review. In the process of target recognition and localization, binocular vision technology was commonly used in vision system. The key point of binocular vision technology is stereo matching. Therefore, stereo matching was then reviewed, and the image matching methods in existence can generally be divided into 2 categories, i.e. region-based image matching method and feature-based image matching method. What's more, the problems exist in recognition and localization methods used in the vision system of apple picking robot, including accuracy, effectiveness, character of real-time and universal applicability, were analyzed. Further study will concentrate on optimizing the structure of vision system, optimizing the intelligent algorithms used in the vision system, improving the real-time capability, recognizing and locating apple targets when the apple targets and vision systems are influenced by oscillation, and improving cost performance. The paper has summarized and analyzed vision system of apple picking robot comprehensively, which can provide reference for future research. [ABSTRACT FROM AUTHOR]

The application of image recognition technology in apple fruit automatic picking and selecting process is an important way for the development of apple industry. At present, the apple image identification and detection take long time and its recognition rate is low. The paper analyzes the image denoising, feature analysis, feature extraction and other key issues, and focuses on occlusion of apple fruit recognition method. Based on the Otsu adaptive threshold segmentation method, an apple detection technology based on local maxima is proposed. Experimental results show7 that the method can accurately extract the characteristics of apple fruit compared with the traditional identification method and local maxima method, especially, for adjacent and occluded the apple image recognition, it maintains a high rate of accuracy. The device can greatly improve automatic level of picking robot for apple. [ABSTRACT FROM AUTHOR]