Car detection by fusion of HOG and causal MRF

Abstract

Detection of cars has a high variety of civil and military applications, e.g., transportation control, traffic monitoring, and surveillance. It forms an important aspect in the deployment of autonomous unmanned aerial systems in rescue or surveillance missions. In this paper, we present a two-stage algorithm for detecting automobiles in aerial digital images. In the first stage, a feature-based detection is performed, based on local histogram of oriented gradients and support vector machine classification. Next, a generative statistical model is used to generate a ranking for each patch. The ranking can be used as a measure of confidence or a threshold to eliminate those patches that are least likely to be an automobile. We analyze the results obtained from three different types of data sets. In various experiments, we present the performance improvement of this approach compared to a discriminative-only approach; the false alarm rate is reduced by a factor of 7 with only a 10% drop in the recall rate

Research on the Style Classification Method of Clothing Commodity Images

“…Finally, a good effect was achieved and designed and implemented a clothing image retrieval system. Madhogaria et al [13,14] proposed a novel vehicle recognition method that used HOG features and MRF fusion in vehicle detection of aerial digital images. Alsahwa et al [15] used the method of extracting HOG features and putting them into SVM classifier in the Marine biometric recognition system to solve the target recognition task under this background.…”

Vehicle Detection in Remote Sensing Images Using Deep Neural Networks and Multi-Task Learning

“…The framework in (Liu et al, 2016b) applies Gauss process (GP) classification and gradient based segmentation algorithm (GSEG) to realize vehicle probability estimation of each pixel. Histogram of directional gradient feature descriptor (HOG) (Dalal, Triggs, 2005) and linear support vector machine (SVM) are used in (Bougharriou et al, 2017), (Madhogaria et al, 2015). Work (Kembhavi et al, 2010) uses color probability maps, pixel pairs and HOG to depict the color and geometric structure properties.…”

Car Detection in Aerial Images of Dense Urban Areas

“…In a different fashion, Razakarivony and Jurie [18] trained two different classifiers one for the foreground and the other for the background on different features including raw pixel values, gradients and HOG features. Recently, Madhogaria et al [19] used HOG features to detect cars in a two-stage classification process.…”

“…In the case of having more than one bounding box matching the same ground truth, only one of them was considered a true detection and others were considered false positives. Ambiguous objects, for example objects which are partially occluded were not taken into account, when measuring the performance of the proposed framework as in [16], [17], [19].…”