Search Results

Traffic light detection has great significant for unmanned vehicle and driver assistance system. Meanwhile many detection algorithms have been proposed in recent years. However, traffic light detection still cannot achieve a desirable result under complicated illumination, bad weather condition and complex road environment. Besides, it is difficult to detect multi-scale traffic lights by embedded devices simultaneously, especially the tiny ones. To solve these problems, this paper presents a robust vision-based method to detect traffic light, the method contains main two stages: the region proposal stage and the traffic light recognition stage. On region proposal stage, we utilize lane detection to remove partial background from the original image. Then, we apply adaptive canny edge detection to highlight region proposal in Cr color channel, where red or green color proposals can be separated easily. Finally, extract the enlarged traffic light RoI (Region of Interest) to classify.

Forward obstacles detection is one of the key tasks in the perception system of autonomous vehicles. The perception solution differs from the sensors and the detection algorithm, and the vision-based approaches are always popular. In this paper, an embedding fast obstacles detection algorithm is proposed to efficiently detect forward diverse obstacles from the image stream captured by the monocular camera. Specifically, our algorithm contains three components. The first component is an object detection method using convolution neural networks (CNN) for single image. We design a detection network based on shallow residual network, and an adaptive object aspect ratio setting method for training dataset is proposed to improve the accuracy of detection. The second component is a multiple object tracking method based on correlation filter for the adjacent images.

In recent years, due to its strong plasticity and excellent future potential, the development of automated vehicles in the mining environment is extraordinarily rapid. The application of lidar in automated vehicles has also become more and more popular, and algorithms for point cloud object detection have emerged endlessly. However, due to rough road and dusk-to-dawn operations in the mining scenario and the large size of the truck, traditional detection algorithms fail to meet the requirements of real-time updates. Due to the high precision and efficiency of the deep learning network, its application could break through the limitations of traditional algorithms. In this paper, the algorithm called PointPillars is adapted for object detection in the mining scenario. After converting the point cloud to a sparse pseudo-image and extracting features by a two-dimensional convolutional neural network (2D CNN), the time consumption of the entire algorithm becomes much less.