Multi-feature Fusion and PCA Based Approach for Efficient Human Detection

Detection of human beings in a complex background environment is a great challenge in the area of computer vision. For such a difficult task, most of the time no single feature algorithm is rich enough to capture all the relevant information available in the image. To improve the detection accuracy we propose a new descriptor that fuses the local phase information, image gradient, and texture features as a single descriptor and is denoted as fused phase, gradient and texture features (FPGT). The gradient and the phase congruency concepts are used to capture the shape features, and a centersymmetric local binary pattern (CSLBP) approach is used to capture the texture of the image. The fusing of these complementary features yields the ability to localize a broad range of the human structural information and different appearance details which allow for more robust and better detection performance. The proposed descriptor is formed by computing the phase congruency, the gradient, and the CSLBP value of each pixel with respect to its neighborhood. The histogram of oriented phase and histogram of oriented gradient, in addition to CSLBP histogram are extracted for each local region. These histograms are concatenated to construct the FPGT descriptor. Principal components analysis (PCA) is performed to reduce the dimensionality of the resultant features. Several experiments were conducted to evaluate the detection performance of the proposed descriptor. A support vector machine (SVM) classifier is used in these experiments to classify the FPGT features. The results show that the proposed algorithm has better detection performance in comparison with the state of art feature extraction methodologies.