ASSET-2: Real-Time Motion Segmentation and Shape Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
A cascade of boosted generative and discriminative classifiers for vehicle detection
EURASIP Journal on Advances in Signal Processing
Hi-index | 0.00 |
This study suggests a method to detect multiple vehicles, which is important for driving assistance system. In a frame of color image, shadow information and edge elements are used to detect vehicle candidate areas. Detecting the areas of multiple vehicles requires to analyze Estimation of Vehicle (EOV) and Accumulated Similarity Function (ASF) from the vehicle candidate areas that exist in image sequences. Later by evaluating the possibility of vehicles, it determines the vehicle areas. Most studies focus on detecting a single vehicle in front. This study, however, focuses on detecting multiple vehicles even in heavy traffic and frequent change of lanes.