Front and Rear Vehicle Detection and Tracking in the Day and Night Times Using Vision and Sonar Sensor Fusion

Vision-based vehicle detection for a driver assistance system

This paper proposes a computer vision vehicle detection algorithm. The main focus of this proposed algorithm, in which the vehicle is detected based on dynamic traffic scenes. The scene can be recorded using on-board camera that fixed in position to monitor the front traffic. The method that proposed in this vehicle detection algorithm is based on underneath vehicle shadows. The shadows underneath vehicle have a higher intensity compared to the background and road area which advantageous as the main feature for detection. To achieve low computational complexity, the edges feature is detected using a horizontal Sobel operator, which is enhanced by using Scharr operator. Together with blob analysis to detect the wanted features and bounding box is used to label the vehicle detected in the final detection. The algorithm test result shows that the method is effective in the vehicle detection and display a highly accurate result.

Vehicle detection based on underneath vehicle shadow using edge features

Vehicle detection is a fundamental task in Forward Collision Avoiding Systems (FACS). Generally, vision-based vehicle detection methods consist of two stages: hypotheses generation and hypotheses verification. In this paper, we focus on the former, presenting a feature-based method for on-road vehicle detection in urban traffic. Hypotheses for vehicle candidates are generated according to the shadow under the vehicles by comparing pixel properties across the vertical intensity gradients caused by shadows on the road, and followed by intensity thresholding and morphological discrimination. Unlike methods that identify the shadow under a vehicle as a road region with intensity smaller than a coarse lower bound of the intensity for road, the thresholding strategy we propose determines a coarse upper bound of the intensity for shadow which reduces false positives rates. The experimental results are promising in terms of detection performance and robustness in day time under different weather conditions and cluttered scenarios to enable validation for the first stage of a complete FACS.

Shadow-based vehicle detection in urban traffic

Vehicle tracking and detection techniques using IoT

A video-based vehicle detection method must be capable of continual operation under various environmental and illumination conditions. Therefore, identifying features that can adapt to various conditions is crucial. This paper proposes a robust vehicle detection method for identifying horizontal edges by using a Sobel filter to achieve low computational complexity. Based on the orientation of the gradient, the feature of a vehicle can be extracted accurately and quickly. Additionally, symmetrical features are critical features, and a histogram of oriented gradients was employed to reduce the detection error rate. The experimental results indicate that the proposed method can efficiently and effectively detect forward vehicle in various scenes.

Ming-Hua Li

Papers

Edge-based forward vehicle detection method for complex scenes