Detecting partially occluded vehicles with geometric and likelihood reasoning

• Published in: IET computer vision Vol. 9; no. 2; pp. 174 - 183
• Main Authors: Yu, Teng, Shin, Hyunchul
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 01.04.2015; Wiley
• Subjects: Algorithms; Benchmarks; binary map; Computer vision; geometric reasoning; geometry; hypothesis veriflcation method; image denoising; likelihood reasoning; median filters; median fllter; Noise; noise elimination; object detection; Occlusion; occlusion dataset synthesis; occlusion hypothesis; partially occluded vehicle detection; patch scoring; positive region; real-world scenes; Scoring; statistical analysis; statistical approach; traffic engineering computing; Training; union-flnd algorithm; vehicle-background occlusions; vehicle-vehicle occlusions; Vehicles; visual databases; median filters; geometric reasoning; noise elimination; visual databases; positive region; vehicles; object detection; traffic engineering computing; image denoising; median fllter; hypothesis veriflcation method; occlusion dataset synthesis; likelihood reasoning; partially occluded vehicle detection; binary map; vehicle-vehicle occlusions; geometry; statistical analysis; occlusion hypothesis; patch scoring; vehicle-background occlusions; union-flnd algorithm; statistical approach; real-world scenes
• ISSN: 1751-9632; 1751-9640; 1751-9640
• DOI: 10.1049/iet-cvi.2013.0334

In real-world scenes, vehicles are frequently overlapped by other objects and various backgrounds. In this study, an effective method to detect such vehicles, especially those partially occluded by nearby vehicles or other objects is presented. The authors have developed a statistical approach to generate occlusion hypothesis and a new hypothesis verification method. To verify occlusion hypothesis, the verification method utilises geometric and likelihood information. In this way, both vehicle–background and vehicle–vehicle occlusions can be detected. No additional occlusion-specific training is required. In addition, a median filter is applied to eliminate the noise in the patch scoring, and a union-find algorithm is used to find the connected positive region in the binary map. A synthesised occlusion dataset is created to test the performance, and the experimental results on popular benchmarks indicate that the proposed method is effective and robust in recognising partially occluded vehicles.