This paper proposes a quadratic classification approach on the subspace of Extended Histogram of Gradients (ExHoG) for human detection. By investigating the limitations of Histogram of Gradients (HG) and Histogram of Oriented Gradients (HOG), ExHoG is proposed as a new feature for human detection. ExHoG alleviates the problem of discrimination between a dark object against a bright background and vice versa inherent in HG. It also resolves an issue of HOG whereby gradients of opposite directions in the same cell are mapped into the same histogram bin. We reduce the dimensionality of ExHoG using Asymmetric Principal Component Analysis (APCA) for improved quadratic classification. APCA also addresses the asymmetry issue in training sets of human detection where there are much fewer human samples than non-human samples. Our proposed approach is tested on three established benchmarking data sets--INRIA, Caltech, and Daimler--using a modified Minimum Mahalanobis distance classifier. Results indicate that the proposed approach outperforms current state-of-the-art human detection methods.

This paper proposes two sets of novel edge-texture features, Discriminative Robust Local Binary Pattern (DRLBP) and Ternary Pattern (DRLTP), for object recognition. By investigating the limitations of Local Binary Pattern (LBP), Local Ternary Pattern (LTP) and Robust LBP (RLBP), DRLBP and DRLTP are proposed as new features. They solve the problem of discrimination between a bright object against a dark background and vice-versa inherent in LBP and LTP. DRLBP also resolves the problem of RLBP whereby LBP codes and their complements in the same block are mapped to the same code. Furthermore, the proposed features retain contrast information necessary for proper representation of object contours that LBP, LTP, and RLBP discard. Our proposed features are tested on seven challenging data sets: INRIA Human, Caltech Pedestrian, UIUC Car, Caltech 101, Caltech 256, Brodatz, and KTH-TIPS2-a. Results demonstrate that the proposed features outperform the compared approaches on most data sets.

Despite superior performance of Local Binary Pattern (LBP) in texture classification and face detection, its performance in human detection has been limited for two reasons. Firstly, LBP differentiates a bright human from a dark background and vice-versa. This increases the intra-class variation of humans. Secondly, LBP is contrast and illumination invariant. It does not discriminate between weak contrast local regions and similar strong contrast ones, resulting in a similar feature representation. Non-Redundant LBP (NRLBP) has been proposed to solve the first issue of LBP. However, an inherent limitation of NRLBP is that LBP codes and their complements in the same block are mapped to the same code. Furthermore, NRLBP, like LBP, is also contrast and illumination invariant. In this paper, we propose a novel edge-texture feature, Discriminative Robust Local Binary Pattern (DRLBP), for human detection. DRLBP alleviates the problems of LBP and NRLBP by considering the weighted sum and absolute difference of a LBP code and its complement. Our experimental results show that DRLBP consistently outperforms LBP and NRLBP for human detection.

In this paper, we present a parts-based modeling framework using Extended Histogram of Gradients (ExHoG) for object detection. Visual object detection is a challenging issue in computer vision where objects need to be detected in varying illumination and contrast environments. Furthermore, objects belonging to the same class exhibit large intra-class variations. Here, we propose using ExHoG with the discriminatively trained deformable part models of Felzenszwalb et. al. [1]. This framework is based on mixtures of multiscale deformable part models. ExHoG is a novel feature proposed earlier for the purpose of human detection and has shown promising results against other state-of-the-art approaches. The proposed approach is tested on INRIA Human data set and the PASCAL VOC 2007 data set. Results demonstrate superior performance on INRIA compared to existing state-of-the-art approaches and improved performance on PASCAL VOC 2007.

Unsigned Histogram of Gradients (UHoG) is a popular feature used for human detection. Despite its superior performance as reported in recent literature, an inherent limitation of UHoG is that gradients of opposite directions in a cell are mapped into the same histogram bin. This is undesirable as it will produce the same UHoG feature for two different patterns. To address this problem, we propose a new feature named the Extended Histogram of Gradients (ExHoG) in this paper. It comprises two components: UHoG and a histogram of absolute bin value differences of opposite gradient directions computed from Histogram of Gradients (HoG). Our experimental results show that the proposed ExHoG consistently outperforms the standard HoG and UHoG for human detection.