Survey of Pedestrian Detection for Advanced Driver Assistance Systems

Abstract

Abstract-Advanced driver assistance systems (ADASs), and particularly pedestrian protection systems (PPSs), have become an active research area aimed at improving traffic safety. The major challenge of PPSs is the development of reliable on-board pedestrian detection systems. Due to the varying appearance of pedestrians (e.g., different clothes, changing size, aspect ratio, and dynamic shape) and the unstructured environment, it is very difficult to cope with the demanded robustness of this kind of system. Two problems arising in this research area are the lack of public benchmarks and the difficulty in reproducing many of the proposed methods, which makes it difficult to compare the approaches. As a result, surveying the literature by enumerating the proposals one-after-another is not the most useful way to provide a comparative point of view. Accordingly, we present a more convenient strategy to survey the different approaches. We divide the problem of detecting pedestrians from images into different processing steps, each with attached responsibilities. Then, the different proposed methods are analyzed and classified with respect to each processing stage, favoring a comparative viewpoint. Finally, discussion of the important topics is presented, putting special emphasis on the future needs and challenges.

Pedestrian detection based on hierarchical co-occurrence model for occlusion handling

“…In the following experiments, the state-of-the-art approaches can be compared with our approach, as they are also trained from the INRIA dataset. The labels and evaluation code provided by Dollar et al online are used for evaluating the criteria proposed in [10]. We focus on the reasonable subset, i.e., images with 50 pixels or larger, and non-occluded or partially occluded pedestrians.…”

“…The performance of our proposed hierarchical model is compared with other relevant stateof-the-art approaches, which are HOG [7], HOGLBP [13], MultiFtr [5], ChnFtrs [4], LatSVM-V2 [6], VeryFast [2], MT-DPM [1], Random Forest [3], FPDW [27], and Random Subspace [17]. As [10] proposed the evaluation criteria, log-average miss rate is used to summarize the detector performance. The performance is computed by averaging miss rate at FPPI rates evenly spaced in log-space within the range of 10 À 3 -10 0 .…”

“…Pedestrian detection is an important topic for practical applications, such as video surveillances [9,29], intelligent vehicles [10], and robot sensing. State-of-the-art algorithms have been used for achieving progress on pedestrian detection.…”

Real Time People Detection Combining Appearance and Depth Image Spaces Using Boosted Random Ferns

“…It has been proved that image HOG space is more robust to illumination and object appearance changes, obtaining substantial gains over features based on the appearance RGB domain. For a deeply analysis of the state-of-the-art in vison-based pedestrian detectors, the reader is referred to recent surveys and benchmarks, i.e [2], [6], [11], [5], [7].…”

Tracking and intercepting pedestrians: a robotic approach to surveillance of critical infrastructures

“…Intelligent systems have improved the surveillance and safety of public places [12]. More recently, commercial cars have been equipped with systems for active pedestrian detection and avoidance [13,14]. Similarly, similar systems are being deployed in service robots [15].…”