Kinect‐Based Pedestrian Detection for Crowded Scenes

Abstract

Pedestrian movement data including volumes, walking speeds, and trajectories are essential in transportation engineering, planning, and research. Although traditional image‐based pedestrian detectors provide very rich information, their performance degrades quickly with increased occurrence of occlusion. The three‐dimensional sensing capabilities of Microsoft's Kinect present a potential cost‐effective solution for occlusion‐robust pedestrian detection. This article proposes an efficient pedestrian detection approach for crowded scenes by fusing RGB and depth images from the Kinect. More specifically, we first extract the pedestrian contour regions from RGB images using background subtraction. Then, we develop a region clustering algorithm to extract pedestrians from the contour regions using depth information. Finally, a tracking and counting algorithm is designed to acquire pedestrian volumes. The proposed approach was proven effective with an average detection accuracy of 93.1% at 20 frames per second. These results demonstrate the feasibility of using the low‐cost Kinect device for real‐world pedestrian detection in crowded scenes.

Edge‐Enhanced Matching for Gradient‐Based Computer Vision Displacement Measurement

“…Vision sensors, among these new techniques, have been broadly applied for civil engineering problems. Famous applications of vision‐sensing techniques include dynamic displacement monitoring (Cha et al., ; Park et al., ; Yoon et al., ), three‐axes (i.e., X‐axis, Y‐axis, and depth) displacement measurement (Park et al., ; Abdelbarr et al., ), surface displacement/strain measurement (Luo et al., ; Almeida et al., ), vision‐based structural analysis (Chen et al., ; Sharif et al., ; Park et al., ), cable tensile force evaluation (Kim et al., ), bridge‐lining inspection (Zhu et al., ), rocking motion and landslide monitoring (Debella‐Gilo and Kääb, ; Greenbaum et al., ), automatic construction progress assessment (Bügler et al., ), 3D object finding in point cloud (Sharif et al., ), surface crack/defection detection based on texture‐based video processing (Cord and Chambon, ; Chen et al., ) or deep learning (Cha et al., ; Cha et al, ; Zhang et al., ), vehicle classification based on spectrogram features (Yeum et al., ), and intelligent transportation (Chen et al., ; Fernandez‐Llorca et al., ). With advancement in image sensors and computer techniques such as computer vision, cloud computing, and wireless data transfer, vision sensors have become more cost‐effective and computation‐efficient, thus have high potential in field application for SHM problems.…”

Computer‐Aided Optimization of Surveillance Cameras Placement on Construction Sites

“…Surveillance camera is nonintrusive to general construction tasks without attaching tag to workers or their proactive equipment (Park et al., ; Rezazadeh Azar and McCabe, ). With the advancement of computer vision techniques on construction sites, cameras become significant in numerous implementations such as (a) detecting and tracking construction‐related entities to calculate productivity (Chi et al., ; Gong and Caldas, ; Brilakis et al., ; Chi and Caldas, , ; Gong et al., ) and avoiding collisions (Chen et al., ; Hamledari et al., ); (b) recognizing working condition and environmental context to monitor construction progress and obtain safety context (Gualdi et al., ; Park and Brilakis, ); (c) tracking workforce and detecting motions to prevent proximity to hazards (Teizer and Vela, ; Yang et al., ) and preventing muscular injuries from awkward postures or ergonomic risks (Ray and Teizer, ; Han and Lee, ; Han et al., ; Yang et al., ); (d) monitoring and identifying damages and quality issues (Salem et al., ; Yeum and Dyke, ; Cha et al., ; Cha et al., ; Kong and Li, ), especially visual cracks (Chen et al., ; Zhang et al., ); (e) inspecting structural conditions in hazardous environment (Zhu et al., ; Oh et al., ; Park et al., ); and (f) reconstructing building models (Fleishman et al., ; Olague and Mohr, ). Based on the diverse applications of surveillance cameras, intelligible information is extracted automatically in real time, offering an effective solution to time‐ and labor‐consuming inspections on construction sites (Mirchandani et al., ).…”

Detecting Small Scale Pedestrians and Anthropomorphic Negative Samples Based on Light-Field Imaging

“…Hsieh et al [13] proposed a people counting system with Kinect achieving almost 100% bi-directional counting and real-time detecting. Chen et al [14] detected people in crowded scenes by fusing RGB and depth images from Kinect. Premebida et al [15] used the context-based multisensor for pedestrian detection in urban environment.…”