A direct approach for object detection with catadioptric omnidirectional cameras. Issue 2 (February 2016)

• Record Type: Journal Article
• Authors: Cinaroglu, Ibrahim; Bastanlar, Yalin
• Is Part Of: Signal, image and video processing. Volume 10:Issue 2(2016)
• Page Start: 413
• Page End: 420
• Publication Date: 2016-02
• Subjects: Catadioptric omnidirectional cameras -- Object detection -- Human detection -- Car detection -- Vehicle detection; Signal processing -- Digital techniques -- Periodicals; Image processing -- Digital techniques -- Periodicals; Digital video -- Periodicals; 621.3822
• DOI: 10.1007/s11760-015-0768-2
• Languages: English
• ISSNs: 1863-1703

Abstract

Abstract In this paper, we present an omnidirectional vision-based method for object detection. We first adopt the conventional camera approach that uses sliding windows and histogram of oriented gradients (HOG) features. Then, we describe how the feature extraction step of the conventional approach should be modified for a theoretically correct and effective use in omnidirectional cameras. Main steps are modification of gradient magnitudes using Riemannian metric and conversion of gradient orientations to form an omnidirectional sliding window. In this way, we perform object detection directly on the omnidirectional images without converting them to panoramic or perspective images. Our experiments, with synthetic and real images, compare the proposed approach with regular (unmodified) HOG computation on both omnidirectional and panoramic images. Results show that the proposed approach should be preferred.