A Taillight Matching and Pairing Algorithm for Stereo-Vision-Based Nighttime Vehicle-to-Vehicle Positioning

Abstract

The stereo vision system has several potential benefits for delivering advanced autonomous vehicles compared to other existing technologies, such as vehicle-to-vehicle (V2V) positioning. This paper explores a stereo-vision-based nighttime V2V positioning process by detecting vehicle taillights. To address the crucial problems when applying this process to urban traffic, we propose a three-fold contribution as follows. The first contribution is a detection method that aims to label and determine the pixel coordinates of every taillight region from the images. Second, a stereo matching method derived from a gradient boosted tree is proposed to determine which taillight in the left image a taillight in the right image corresponds to. Third, we offer a neural-network-based method to pair every two taillights that belong to the same vehicle. The experiment on the four-lane traffic road was conducted, and the results were used to quantitatively evaluate the performance of each proposed method in real situations.

Deep Hierarchical Rear‐Lamp Tracking at Nighttime

“…Non‐deep‐learning rear‐lamp detection at nighttime has been extensively studied [18]. To sample the candidate region of rear lamps, Chen et al .…”

“…Non-deep-learning rear-lamp detection at nighttime has been extensively studied [18]. To sample the candidate region of rear lamps, Chen et al [6] exploited the contrast between the lighting rear lamp and dark background to sample candidates, for which RGB images were transferred to single-channel images.…”

Active Perception in Non-Visual Recognition Environments by Stretchable Tentacle Sensor Arrays

“…Visual recognition lays the foundation for artificial intelligence science and is crucial for various applications, including space exploration, , smart vehicles, − internet of things, − advanced manufacturing, , and others. − Visual recognition technology mainly depends on the optical information collection, as well as further process and analysis through visual processing algorithms to acquire symbolic descriptions of the scenes, thereby identifying the objects or environments. However, aimed objects might exist in light-interference or dark environments, such as smoke fogs, caves, muddy water, or other surroundings that greatly disturb the collection of optical information.…”