Efficient detection of pavement cracks can effectively prevent traffic accidents and reduce pavement maintenance costs. In order to overcome the complicated and uneconomical disadvantages of traditional crack detection methods, this paper introduces a pavement crack detection network based on deep learning, which can automatically detect pavement cracks and achieves excellent detection accuracy. And the network can easily use the sensors to collect data to facilitate industrial applications. In additional, considering that most cracks have slim feature, we apply the latest Transformer module in the network to improve the effect of cracks detection. Transformer has a strong ability to capture the long-range dependence of the cracks, which enables the network to learn the context information of the crack region. Furthermore, the network also utilizes some techniques to improve the ability of algorithm to detect various cracks. Our network is trained on pavement data sets containing India, the Czech Republic and Japan. It achieved F1 scores of 0.6739 and 0.6650 on two online test sets with fewer network parameters.

Automatic detection of pavement crack is an important task for conducting road maintenance. However, as an important part of the intelligent transportation system, automatic pavement crack detection is challenging due to the poor continuity of cracks, the different width of cracks, and the low contrast between cracks and the surrounding pavement. This study proposes a novel pavement crack detection method based on an end‐to‐end trainable deep convolution neural network. The authors build the network using the encoder–decoder architecture and adopt a pyramid module to exploit global context information for the complex topology structures of cracks. Moreover, they introduce a spatial‐channel combinational attention module into the encoder–decoder network for refining crack features. Further, the dilated convolution is used to reduce the loss of crack details due to the pooling operation in the encoder network. In addition, they introduce a lovász hinge loss function, which is suitable for small objects. They train the authors' network on the CRACK500 dataset and evaluate it on three pavement crack datasets. Among the methods they compare, their method can achieve the best experimental results.

Vehicle counting from an unmanned aerial vehicle (UAV) is becoming a popular research topic in traffic monitoring. Camera mounted on UAV can be regarded as a visual sensor for collecting aerial videos. Compared with traditional sensors, the UAV can be flexibly deployed to the areas that need to be monitored and can provide a larger perspective. In this paper, a novel framework for vehicle counting based on aerial videos is proposed. In our framework, the moving-object detector can handle the following two situations: static background and moving background. For static background, a pixel-level video foreground detector is given to detect vehicles, which can update background model continuously. For moving background, image-registration is employed to estimate the camera motion, which allows the vehicles to be detected in a reference coordinate system. In addition, to overcome the change of scale and shape of vehicle in images, we employ an online-learning tracker which can update the samples used for training. Finally, we design a multi-object management module which can efficiently analyze and validate the status of the tracked vehicles with multi-threading technique. Our method was tested on aerial videos of real highway scenes that contain fixed-background and moving-background. The experimental results show that the proposed method can achieve more than 90% and 85% accuracy of vehicle counting in fixed-background videos and moving-background videos respectively.

Engineering vehicles intrusion detection is a key problem for the security of power grid operation, which can warn of the regional invasion and prevent external damage from architectural construction. In this paper, we propose an intelligent surveillance method based on the framework of Faster R-CNN for locating and identifying the invading engineering vehicles. In our detection task, the type of the objects is varied and the monitoring scene is large and complex. In order to solve these challenging problems, we modify the network structure of the object detection model by adjusting the position of the ROI pooling layer. The convolutional layer is added to the feature classification part to improve the accuracy of the detection model. We verify that increasing the depth of the feature classification part is effective for detecting engineering vehicles in realistic transmission lines corridors. We also collect plenty of scene images taken from the monitor site and label the objects to create a fine-tuned dataset. We train the modified deep detection model based on the technology of transfer learning and conduct training and test on the newly labeled dataset. Experimental results show that the proposed intelligent surveillance method can detect engineering vehicles with high accuracy and a low false alarm rate, which can be used for the early warning of power grid surveillance.

Person re-identification is an important surveillance task of searching and identifying pedestrian across different images or video frames. Despite a significant progress has been made in person re-identification based on RGB image sensors, few work focus on the person re-identification between RGB and infrared images, which is a challenging cross-modality problem and has been widely encountered in a dark environment or at night. In addition to the challenges for the same identity associated with variations in camera viewpoints and person poses, there is a non-negligible shift across different sensor modalities since the visual characteristics from RGB and infrared images are heterogeneous. In this paper, we propose a novel end-to-end dual-path multi-branch network for RGB-infrared cross-modality person re-identification, which introduces the multi-branch deep network architecture. The experimental results obtained with SYSU-MM01 datasets indicate that the proposed method can successfully transfer descriptive visual characteristic between RGB and infrared sensor modality. It can significantly outperform state-of-the-art conventional methods and convolutional neural network methods.

Urban parking management is receiving significant attention because of the explosive increase in the number of vehicles. This paper proposes a novel parking occupancy detection method based on a Haar-AdaBoosting algorithm and a convolutional neural network (CNN), which provides intelligent video surveillance in public parking areas, especially gas stations. A key step in this method is accurate, real-time detection of vehicles. An initial set of sub-windows, which contain possible vehicle regions, are obtained by the Haar-AdaBoosting cascade classifier, and these sub-windows are passed to the CNN to filter out non-vehicle regions. Then, we propose a method of parking occupancy detection to recognize which parking spaces are occupied. This method can also recognize illegal occupancy. Our experimental results show that the proposed vision-based method of parking occupancy detection for gas stations is capable of suppressing false positive and can recognize parking occupancy effectively.