Search

Visual localization achieves indoor localization by matching visual data (collected by camera) with visual features of an environment. However, visual feature matching requires a long computation time, which makes it difficult to provide a continuous localization result. Besides, for environment with sparse visual data (e.g. images), it is also difficult to achieve continuous indoor localization using only visual feature matching. To solve this problem, this study proposes a continuous indoor localization approach using perceptual Hash algorithm (pHash) and spatial-constrained image searching strategies. It realizes accurate indoor localization by matching the collected video frames (from smartphone) with the images from a generated indoor image dataset. To improve the efficiency of visual feature matching, a two-level image searching and matching strategy is designed, including a pHash-based global searching strategy and a local strategy considering motion continuity. Based on the two-level strategy, a continuous indoor visual localization algorithm is proposed, which can increase the spatial continuity of localization result by integrating both visual localization and dead reckoning. Besides, this algorithm employs a structure from motion method to improve its heading estimation accuracy. Experimental results show that the localization errors of the image querying, continuous offline localization and online localization of this method are approximately 0.70, 0.86 and 0.93 m, respectively, which achieves sub-meter level localization accuracy. In the online localization condition, its average computation time is about 0.42 s, which can provide continuous visual localization.

The higher the automatic driving degree, the higher requirements of a high definition map. Intelligent high definition maps can provide information for L5 level autonomous vehicles, which is an important direction for the development of high definition maps in the future. According to the current high definition map construction methods, the definition of multi-agent collaborative intelligent high definition map construction is proposed. Its construction framework and key technologies: multi-agent routing for data collection, multi-source heterogeneous integration data fusion and expression, road scene cognition, intelligent high definition map fusion, intelligent high-definition update are studied, and their corresponding appropriate technical schemes are proposed. Besides, the challenges in the further construction process are analyzed.

The dynamic precision engineering survey is not only used in the construction but also in monitoring the dynamic change during usage. With the rapid popularization of various sensors and automated mobile platform, such as intelligent vehicles, unmanned aerial vehicle (UAV), unmanned ship, robots etc., the engineering survey is upgraded in an automated, dynamic and intelligent way. It is now armed with the ability to survey in movement. Surveying devices, including mature surveying robots, mobile surveying vehicle, etc., have been proposed. Another way is to assemble devices delicately for specific applications, which can achieve dynamic and precise measurements of position, posture, internal deform and external shape. Focusing on the intelligent device with integrated sensors and specific applications, this paper puts forward the integration principle of multiple sensors and the advanced data processing methods for intelligent engineering surveying. This paper also demonstrates several applications of these devices, such as internal deformation monitoring of the rockfill dam, damage monitoring of the urban underground water pipelines, surveying of the road damages and the damage detection on the south-to-north water diversion project (SNWDP), to show different requirements and solutions in different applications.

For narrow areas such as corridors, the positioning accuracy can be significantly improved by using behavioral landmarks and electronic indoor maps. However, in wide indoor areas without linear constraints,such as offices, shops and airport halls, the use of inertial sensors and indoor map cannot achieve a significant performance gain. Virtual access point (AP) is the "virtual position" of AP calculated by using the simplified formula of wireless signal attenuation with reference points.Based on this, a fingerprint point clustering algorithm based on virtual AP coordinates has been proposed in offline phase. An AP selection algorithm based on eight-diagram has been proposed to reduce the calculation amount of online positioning. Finally, experiments conducted in different office buildings demonstrated that the positioning accuracy of the proposed algorithms is considerably better than that of the traditional methods.

Electric taxis have been demonstrated with the promotion of electric vehicles. Compared with internal combustion engine vehicles, electric taxis spend more time in recharging, which reduces the taxi drivers’ intention to use. Reinforcement learning is applicable to the sequential decision-making process of taxis driver. This paper presents the double deep Q-learning network (DDQN) model to simulate the operation of electric taxis. According to the real-time state of taxis, DDQN will choose the optimal actions to execute. After training, we obtain a global optimal electric taxi service strategy, and finally optimize the taxi service. Using real-world taxi travel data, an experiment is conducted in Manhattan Island in New York City, USA. Results show that, comparing with the baseline methods, DDQN reduces the waiting time for charging and the rejection rate by 70% and 53%, respectively. Taxi drives’ income are finally increased by about 7%. Moreover, the results of model parameter sensitivity analysis indicate that the charge speed and the number of vehicles have greater impact on drives’ income than the battery capacity. When the charging rate reaches 120 kW, electric taxis achieve the best performance. The government should build more fast charging station to improve the revenue of electric taxis.

The rapid spread of the novel coronavirus (COVID-19) from late 2019 to early 2020 poses a huge challenge to the public health of China and the world. The risk assessment of COVID-19 plays an essential role in the decision making of epidemic prevention. As one of the most important metropolitan areas in China, Guangdong-Hong Kong-Macao Greater Bay Area (GBA) is seriously affected by COVID-19. A massive number of returnees after the holidays further poses potential COVID-19 risks. Targeting on the urgent need of COVID-19 risk assessment in GBA, we combine multi-source urban spatiotemporal big data and traditional epidemiological model to design an improved model. Specifically, the improved model introduces dynamic “return-to-work” population and propagation hotspots to calibrate COVID-19 parameters in different assessment units and improve SEIR model suitability in GBA; targeting on the urgent needs of high resolution (e.g. community level) risk assessment, the model utilizes multi-source urban big data (e.g, mobile phone) to improve modelling spatial resolution from more detailed population and COVID-19 OD matrix. The simulation results show that: ① compared with the traditional SEIR model, the proposed model has better capability for risk assessment in GBA; ② the massive population flow in GBA introduces considerable COVID-19 risk in GBA; ③ a variety of epidemic prevention initiatives in China are highly effective for delaying the spread of COVID-19 in GBA.

Promoting neighborhood vibrancy is vital for urban development. Recently, geotagged data provide unprecedented opportunities for discovering urban vibrancy patterns and their affecting mechanism. However, traditional urban vibrancy studies rely on fields survey therefore are time-consuming and highly-cost. This study constructs two urban vibrancy indices using point-of-interest and social media check in data. The spatial patterns of urban vibrancy are explored with spatial auto-regression analytic. Ordinary regression models (OLS) and spatial autoregression models (SAM) are established for revealing the influences of built environment on urban vibrancy by using geospatial data such as land use, roads and buildings. An empirical study in Shenzhen was implemented. The results show that:commercial land, industry land, mixed land use, the road density, and metro stations are five main factors highly influencing Shenzhen vibrancy. Residential land use and building footprints only have significant effects on vibrancy exhibited by POI. These exploratory findings demonstrate that urban vibrancy should be assessed and improved for different consideration.

Indoor localization technology is one of the hot research topics in the field of location-based service (LBS), which has attracted the attention of government, industry and academia. Indoor GIS contains abundant priori knowledge, which can be used for indoor localization. In this paper, we review the research process of GIS-aided indoor localization. We first introduce the state-of-the-art, including map constraints-based indoor localization, topological map matching-based indoor localization, context sensing-based indoor localization, and visual sensing-based indoor localization. Then, we introduce its challenges, including indoor GIS data model in uniform space-time reference, data updating of indoor GIS, and limited computing resource of smartphones. Finally, we forecast the development trend in terms of GIS-aided indoor localization, it will develop from context sensing-based method to spatial cognition-based method. In the aspect of GIS data acquisition, it will develop from machine-based method to human-machine interaction-based method.

In order to study the spatial distribution of maximum coastal zone mapping and imaging LiDAR(CZMIL)detectable depth in the northern South China Sea,we firstly research the existing Kd(490) inversion algorithm in the northern South China Sea.The relationship between the diffuse attenuation coefficient Kd(490) and Kd(532) is established based on the optical profile data measured,and the relationship between the diffuse attenuation coefficient Kd(532) and the maximum CZMIL detectable depth is summarized.Then,using the remote measurement data of the Aqua-MODIS,we obtain the spatial distribution of diffuse attenuation coefficient at 532 nm in the northern South China Sea in January,June and October,2014.It shows that June is more suitable for bathymetry operation than in October and January.Finally,we obtain the spatial distribution of maximum CZMIL detectable depth in June in the northern South China Sea.The results show that the CZMIL detectable water depths in the northern South China Sea are about 0~71.18 m.The study provides a reference for the time selection and flight scheme of LiDAR bathymetry operation in the northern South China Sea.

Concrete defect detection of diversion shafts in large hydropower station has a direct impact on the safe operation of the station,endangering the lives of cities and millions of people downstream.However,the research on the detection of the 100-meter-level shafts is still a blank in the world.It is a "blind spots" in detection field.In this paper,a method of integrating multiple mapping sensors based on unmanned airship is proposed to resolve the international problem of data acquisition and disease detection in vertical profile the diversion shafts in hydropower stations; We have designed a brand new device to acquire data and detect the disease of the shafts:a cylindrical unmanned airship adapted to the shafts environment is the floating loading platform,on which multi-sensors such as panoramic CCD camera,3D laser scanner,inertial measurement unit,barometric altimeter,illumination module and control module etc is integrated.Trial implemented inside the No.2,No.3 and No.4 shafts of Nuozhadu hydropower station from May 2017 to July,indicates that the detection device can be well applied for the overhaul of similar vertical profile.The detecting device fills the gap of 100-meter-level shaft detection field and presents a wide application prospect.

The fuel-consumption and emissions from transportation present severe challenges to the human environment. This article proposes a novel approach of space-time path supported estimation for vehicles' fuel-consumption and emissions. In the proposed approach,space-time paths of vehicles are built under space-time integrated 3-dimensions coordinate firstly and mobile activities (MA) and stationary activities (SA) are extracted from these space-time paths. Then the approach estimates the fuel-consumption and emissions from each Space-Time Path Segment (STPS) and the moving parameters with COPERT model. Finally this article presents an N-Dimensional model for visualizing the moving characteristics,fuel-consumption and emissions of each STPS in an integrated frame. In the case study,fuel-consumption and emissions of a single vehicle and an area of road network are estimated and analyzed using GPS trace data. The results show that the space-time path supported approach is superior to the traditional average speed based approach in the aspects of precision and visualization. The proposed fuel-consumption and emissions estimating approach is effective in energy and emissions information acquisition.

The traditional precise engineering surveying is characterized by manual static discrete observation and geometric model solution,which cannot meet the requirements of large-scale infrastructure such as pavement and track,where need of wide-range,continuous,dynamic and high-precision surveying for these infrastructures' and systems' maintenance and management.The dynamic surveying based on multi-sensor integration technology and the cooperative computing based on multi-source spatial-temporal data are the important development directions for precise engineering surveying.First,the paper introduced the uniform and conversion of high-precision spatial-temporal datum,the multi-sensor synchronous control,the fusion of the observed data,the quality improvement of the surveying data and the feature extraction and recognition of the pavement cracks based on the three-dimensional image.Then,the progress of dynamic and precise surveying applications such as pavement roughness,rutting and deflection survey,as well as geometrical parameters of track,fastener status and rail damage detection are described.

Intersection is an important part of the generation and renewal of urban traffic network. In this paper, a new method was proposed to detect urban intersections automatically from the spatiotemporal big trace data. Firstly, the turning point pairs were based on tracking the trace data collected by vehicles. Secondly, different types of turning point pairs were clustered by using spatial growing clustering method based on angle and distance differences, and the clustering methods of local connectivity was used to recognize the intersection. Finally, the intersection structure of multi-level road network was constructed with the range of the intersection and turning point pairs. Taking the taxi trajectory data in Wuhan city as an example, the experimental results showed that the method proposed in this paper can automatically detect and recognize the road intersection and its structure.

Vehicles' GPS traces collected by crowds have being as a new kind of big data and are widely applied to mine urban geographic information with low-cost, quick-update and rich-informative. However, the growing volume of vehicles' GPS traces has caused difficulties in data processing and their low quality adds uncertainty when information mining. Thus, it is a hot topic to extract high-quality GPS data from the crowdsourced traces based on the expected accuracy. In this paper, we propose an efficient partition-and-filter model to filter trajectories with expected accuracy according to the spatial feature of high-precision GPS data and the error rule of GPS data. First, the proposed partition-and-filter model to partition a trajectory into sub-trajectories based on the constrained distance and angle, which are chosen as the basic unit for the next processing step. Secondly, the proposed method collects high-quality GPS data from each sub-trajectory according to the similarity between GPS tracking points and the reference baselines constructed using random sample consensus algorithm. Experimental results demonstrate that the proposed method can effectively pick up high quality GPS data from crowdsourced trace data sets with the expected accuracy.

The spatio-temporal trajectory of taxi GPS data in streets and small lanes of Wuhan city is taken as the experiment data source, based on the "perceptual-cognition-experience" three levels of cognitive law, a new approach for track fusion and road network generation is put forward from the GPS spatio-temporal trajectories. The experiment with the taxi GPS trajectory in Wuhan is done, and the results are shown us that the proposed method in this paper for the taxi trajectory fusion and road network generation is practicable.

The paper presents a map-matching method which mainly considers the curvature integral value of the curve as a map-matching characteristic for constraining the associated matching between two adjacent GPS track points. Through the implementation of map matching experiments for floating car data on the different conditions of both route categories and sampling intervals, the proposed curvature integration constrained map-matching method could be superior to the classic floating car map matching method when evaluating them by the matching accuracy and stability.

Silymarin is a traditional hepatoprotective herb for the adjuvant therapy of liver diseases, which shows marked pharmacological activities such as antioxidant and anti-inflammatory properties. This paper introduces the action mechanism of silymarin in regulating liver function, ameliorating hepatic fibrosis, protecting pancreatic cells, suppressing the growth of tumor cells, and inhibiting the replication of hepatitis C virus. Silymarin is considered to be a natural medicine with little toxic or side effect at a high dose. It holds promise for anti-tumor, antioxidant, anti-inflammatory, and antiviral application.