Search

Monocular vision system is widely used in many fields due to its simple structure, faster speed, and lower cost for object measurement. However, most of the current monocular methods have complicated mathematical models or require artificial markers to achieve accurate measurement results. In addition, it is not easy to precisely extract the features of objects in the captured image which are affected by many factors. In this paper, we present a semantic-aware monocular projection model for accurate pose measurement. Our mathematical model is simple and neat, and we use deep learning network to extract the semantic features in images. Finally, the relevant parameters of the projection model are further optimized with Kalman filter to make the measurement results more accurate and stable. The extensive experiments demonstrate that the proposed method is robust with high performance and accuracy. As a few constraints are required on the measured object and environment, our method is easy for installation. [ABSTRACT FROM AUTHOR]

In the video surveillance, cameras often jitter slightly because of some uncertain factors like wind, loose of bracket, and so on, which may add more difficulties to subsequent intelligent video analysis. Then, it is great significant to detect whether and how is a camera jittering. In this paper, a concept, i.e. region of reference (ROR), is defined, and a framework and method of surveillance camera jitter detection is proposed through perceiving the location changes of the ROR. First, an extraction model of motion information is established to extract and eliminate the moving information such as moving objects, swaying leaves, etc. Second, global contrast and octree color quantization are employed to filter out the significant regions in the background, then, the most representative regions are chosen as the RORs by tracking the boundary of significant regions. Third, the RORs and their surrounding image features are extracted and input into the filter to construct the response map, then, the corresponding region of peak value in the response map is perceived for location change. Average accuracy of the proposed method on video jitter data set is 95.36%. The experimental results show that the proposed method can solve the problem of video jitter detection in complex scenes. [ABSTRACT FROM AUTHOR]

Vision-based detection of vehicle line-pressing violation has been widely used in intelligent transportation system. However, the accuracy of most current methods is low due to weather, illumination, shooting angle, etc., which increases the workload of manual verification. To cope with these problems, an efficient automatic verification method of vehicle line-pressing violation is proposed based on convolutional neural network (CNN) and geometric projection. First, a CNN model is used to detect vehicles and features are extracted to match the vehicles with line-pressing violation. Second, based on driving direction and vehicle 2D bounding box, pose relationship of the vehicles to the ground is fitted. Finally, according to the relationship between lane line and vehicle chassis range, automatic verification of vehicle line-pressing violation is realized. In the experimental results, the recall rate and accuracy rate reached 90.3 and 99.7% respectively in 200 test samples, which is better than those of current methods. The experimental results show that the proposed method has high accuracy, recall rate and good performance, and can be used for the automatic verification of vehicle line-pressing violation. [ABSTRACT FROM AUTHOR]

With the popularity of cameras, the application of action recognition is more and more extensive. After the emergence of RGB‐D cameras and human pose estimation algorithms, human actions can be represented by a sequence of skeleton joints. Therefore, skeleton‐based action recognition has been a research hotspot. In this paper, a novel 3D Graph Convolutional Network model (3D‐GCN) with space‐time attention mechanism for 2D skeleton data is proposed. Three‐dimensional graph convolution is employed to extract spatiotemporal features of skeleton descriptor that is composed of joint coordinates, frame differences and angles. Meanwhile, different joints and different frames are given different attention to achieve action classification. A zebra crossing pedestrian dataset named ZCP is also provided, which simulates possible pedestrian actions on the zebra crossing in real scenes. Experimental evaluation is carried out on ZCP dataset and NTU RGB+D dataset. Experimental results show that our method is better than current 2D‐based methods and is comparable with 3D methods. [ABSTRACT FROM AUTHOR]

Deep learning methods, particularly Convolutional Neural Network (CNN), have been widely used in hyperspectral image (HSI) classification. CNN can achieve outstanding performance in the field of HSI classification due to its advantages of fully extracting local contextual features of HSI. However, CNN is not good at learning the long-distance dependency relation and dealing with the sequence properties of HSI. Thus, it is difficult to continuously improve the performance of CNN-based models because they cannot take full advantage of the rich and continuous spectral information of HSI. This paper proposes a new Double-Branch Feature Fusion Transformer model for HSI classification. We introduce Transformer into the process of HSI on account of HSI with sequence characteristics. The two branches of the model extract the global spectral features and global spatial features of HSI respectively, and fuse both spectral and spatial features through a feature fusion layer. Furthermore, we design two attention modules to adaptively adjust the importance of spectral bands and pixels for classification in HSI. Experiments and comparisons are carried out on four public datasets, and the results demonstrate that our model outperforms any compared CNN-Based models in terms of accuracy. [ABSTRACT FROM AUTHOR]

Traffic scene visual perception technology is very important for intelligent transportation. Although the emerging panoptic segmentation is the most desirable sensing technology, object detection and semantic segmentation are relatively more mature and have fewer requirements for data annotation. In this paper, a joint object detection and semantic segmentation perception method is proposed for both practicability and accuracy. The proposed method is based on the results of object detection and semantic segmentation. Firstly, the result of basic semantic segmentation is preprocessed according to the principle of entropy. Secondly, the candidate bounding boxes of pedestrians and vehicles are extracted by object detection. Thirdly, candidate bounding boxes are optimized by using a K-means based vertex clustering algorithm. Finally, the contours of scene elements are matched with the results of semantic segmentation. The experimental results on the Cityscapes dataset show that the final perception effect is more susceptible to semantic segmentation results. The theoretical upper limit of the actual perception effect is 95.4% of the ground-truth of panoptic segmentation. The proposed method can effectively combine object detection and semantic segmentation, and achieve perception results similar to panoptic segmentation without additional data annotation. [ABSTRACT FROM AUTHOR]

In recent years, deep learning has been widely used in hyperspectral image (HSI) classification and has shown good capabilities. Particularly, the use of convolutional neural network (CNN) in HSI classification has achieved attractive performance. However, HSI contains a lot of redundant information, and the CNN-based model is limited by the receptive field of CNN and cannot balance the performance and depth of the model. Furthermore, considering that HSI can be regarded as sequence data, CNN-based models cannot mine sequence features well. In this paper, we propose a model named SSA-Transformer to address the above problems and extract spectral-spatial features of HSI more efficiently. The SSA-Transformer model combines a modified CNN-based spectral-spatial attention mechanism and a self-attention-based transformer with dense connection. The SSA-Transformer model can combine the local and global features of HSI to improve the performance of the model. A series of experiments showed that the SSA-Transformer achieved competitive classification accuracy compared with other CNN-based classification methods using three HSI datasets: University of Pavia (PU), Salinas (SA), and Kennedy Space Center (KSC). [ABSTRACT FROM AUTHOR]

In recent years, deep learning has been widely used in hyperspectral image (HSI) classification and has shown good capabilities. Particularly, the use of convolutional neural network (CNN) in HSI classification has achieved attractive performance. However, HSI contains a lot of redundant information, and the CNN-based model is limited by the receptive field of CNN and cannot balance the performance and depth of the model. Furthermore, considering that HSI can be regarded as sequence data, CNN-based models cannot mine sequence features well. In this paper, we propose a model named SSA-Transformer to address the above problems and extract spectral-spatial features of HSI more efficiently. The SSA-Transformer model combines a modified CNN-based spectral-spatial attention mechanism and a self-attention-based transformer with dense connection. The SSA-Transformer model can combine the local and global features of HSI to improve the performance of the model. A series of experiments showed that the SSA-Transformer achieved competitive classification accuracy compared with other CNN-based classification methods using three HSI datasets: University of Pavia (PU), Salinas (SA), and Kennedy Space Center (KSC). [ABSTRACT FROM AUTHOR]

Tire burst of vehicles is one of the main causes of highway accidents. Furthermore, tire aging is the most important cause of tire burst. It will be of great significance to traffic safety, through identifying the tire text code (TTC) to determine whether or not a tire is over the service life. In this article, a coarse-to-fine method of detection and rectification for TTC is proposed. First, text regions are located using the deep convolutional neural network (DCNN) model. Second, through fitting the tire circle curve, the close-up image of TTC is rotated to a positive direction. Third, a text boundary points’ generation strategy is proposed, which is based on the rotating bounding box of each character. Fourth, the curved text is rectified and input to the DCNN recognition model. On the tire image dataset, the detection accuracy of TTC and characters is 94% and 96.5% respectively, and the recognition accuracy is 94.5%. Through additional experimental results, it is proven that the proposed method has strong robustness to illumination and camera shooting angle, which can meet the real-time detection and recognition requirements as well. [ABSTRACT FROM AUTHOR]

Most object detection methods use rectangular bounding boxes to represent the object, while the representative points network (RepPoints) employs a point set to describe the object. The RepPoints can provide more fine-grained localization and facilitates classification. However, it ignores the difference between localization and classification tasks. Therefore, a lightweight RepPoints with decoupling of the sampling point set (LRP-DS) is proposed in this paper. Firstly, the lightweight MobileNet-V2 and Feature Pyramid Networks (FPN) is employed as the backbone network to realize the lightweight network, rather than the Resnet. Secondly, considering the difference between classification and localization tasks, the sampling points of classification and localization are decoupled, by introducing classification free sampling method. Finally, due to the introduction of the classification free sampling method, the problem of the mismatch between the localization accuracy and the classification confidence is highlighted, so the localization score is employed to describe the localization accuracy independently. The final network structure of this paper achieves 73.3% mean average precision (mAP) on the VOC07 test dataset, which is 1.9% higher than original RepPoints with the same backbone network MobileNetV2 and FPN. Our LRP-DS has a detection speed of 20FPS for the input image of (1000, 600), on RTX2060 GPU, which is nearly twice as fast as the backbone network of ResNet50 and FPN. Experimental results show the effectiveness of our method. [ABSTRACT FROM AUTHOR]

The majority of electro-optical devices use transparent conductive oxide (TCO) electrodes such as indium tin oxide (ITO) in their structure. In this study, we manufactured aluminum zinc oxide (AZO) and gallium zinc oxide (GZO) TCO films on glass substrates and demonstrate suitability of these materials for application as transparent electrodes of liquid crystal displays (LCD). We have established a deposition process for the fabrication of AZO and GZO coated glass substrates with average transmittance of 93% and 92% in the visible spectrum, and the sheet resistivity without annealing of ∼120 Ω/□. Using photolithographic patterning and wet etching of AZO and GZO films, we have successfully fabricated laboratory prototypes of twisted nematic, vertical alignment, in-plane switching, and fringe-field switching LCDs. The electro-optical performance of AZO and GZO prototypes is comparable to those of the ITO prototypes of identical design. The AZO and GZO have demonstrated great potential to compete with ITO as low-cost TCOs for display applications. Our findings validated by numerical analyses will be useful for the development of TCOs alternative for display and other optical or electro-optical applications. [ABSTRACT FROM PUBLISHER]

We demonstrate a fringe-field switching nematic liquid crystal with electro-optical behavior modulated by both bulk and surface polymer stabilization. The polymer is formed by ultraviolet irradiation-induced phase separation of various amounts of a reactive monomer in the planar-aligned nematic liquid crystal. Simulation is carried out to verify the effect of anchoring energy. Experimental evidence validates the effect of monomer concentration on transmittance-voltage and response times curves of fringe-field switching cells. The polymer-stabilized alignment with a higher polymer concentration escalates the interaction between the liquid crystal and the polymer structure and increases the surface anchoring energy. The polymer stabilization also improves the dynamic response times of liquid crystal. The enabling polymer-stabilized alignment technique has excellent electro-optical properties such as a very good dark state, high optical contrast, and fast rise and decay times that may lead to development of a wide range of applications. [ABSTRACT FROM AUTHOR]

We demonstrate a fast switching polymer-stabilized fringe-field switching (PS-FFS) liquid crystal mode device with plannar alignment using an ultraviolet-curable reactive mesogen. The polymer stabilization increases the azimuthal anchoring energy and improves the dynamic response. Transmission-voltage curves and microscopic images show the PS-FFS cell can keep a comparable high contrast ratio. [ABSTRACT FROM AUTHOR]

A new method of improving the response time of vertical alignment (VA) liquid crystal devices using surface polymer stabilization is introduced. A minute amount of a reactive monomer and photo-initiator is mixed with a nematic liquid crystal host and the mixture is polymerized under UV light to form sub-micron sized polymer protrusions on the two substrates of the cell with an applied bias voltage. Several kinds of reactive monomers with different molecular structures are tested, and a faster response time and a lower light leakage at dark state are achieved. This finding will be useful for display applications. [ABSTRACT FROM PUBLISHER]

We investigated the effect of the polymerized surfaces on the anchoring energy and pre-tilt angle of liquid crystal alignment. Ultraviolet light-illuminated cell initiates polymerization and produces sub-micron sized polymer protrusions. Experimental evidences reveal the relation between the curing conditions and the resulted pre-tilt angle and anchoring energy of cells. [ABSTRACT FROM AUTHOR]

A liquid crystal device which shows the capacity to perform as an electrical switchable diffraction grating is demonstrated. Periodical modulation in field-induced refractive index was realized in the in-plane switching liquid crystal device with vertical alignment, which resulted in distinct voltage-dependent diffraction patterns. [ABSTRACT FROM AUTHOR]

At present, light curtain is a widely-used method to measure the vehicle profile size. However, it is sensitive to temperature, humidity, dust and other weather factors. In this paper, a lidar-based system with a K-frame-based algorithm is proposed for measuring vehicle profile size. The system is composed of left lidar, right lidar, front lidar, control box and industry controlling computer. Within the system, a K-frame-based methodology is investigated, which include several probable algorithm combinations. Three groups of experiments are conducted. An optimal algorithm combination, A16, is determined through the first group experiments. In the second group experiments, various types of vehicles are chosen to verify the generality and repeatability of the proposed system and methodology. The third group experiments are implemented to compare with vision-based methods and other lidar-based methods. The experimental results show that the proposed K-frame-based methodology is far more accurate than the comparative methods. [ABSTRACT FROM AUTHOR]

A new method to enhance the surface anchoring of vertical alignment liquid crystal devices using surface polymer stabilization is introduced. Mixture made of a nematic liquid crystal and a minute amount of reactive monomer is polymerized to form sub-micron sized polymer protrusions on the two substrates of the cell. Several kinds of monomers are tested. [ABSTRACT FROM AUTHOR]