Hierarchical Part-Template Matching for Human Detection and Segmentation

Lin, Zhe; Davis, Larry S.; Doermann, David; DeMenthon, Daniel

doi:10.1109/iccv.2007.4408975

Cited by 156 publications

(103 citation statements)

References 22 publications

Supporting

Mentioning

102

Contrasting

Unclassified

Order By: Relevance

“…The parts' update instead depends on the part's match score. For each part, a decision is made as whether the part matches or not based on score thresholding of (12). If the part matches, a partial update of its area, perimeter, color histogram, and amount of overlap is performed by using a running average.…”

Section: Model Updatementioning

confidence: 99%

“…humans). In [12,11], the authors have proposed a hierarchical part-template matching approach to simultaneous human detection and segmentation, and its integration with a tracker [19] for tracking purposes. The main difference with our approach is that we do not seek accurate segmentation of the tracked humans at any stage and can therefore rely on algorithms which are simpler and faster in principle.…”

Section: Introduction and Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Tracking people under heavy occlusions by layered data association

Zhang

Perez‐Concha

Piccardi

2014

Multimed Tools Appl

View full text Add to dashboard Cite

One of the main difficulties in video tracking of people arises in scenarios where targets are repeatedly and extensively occluded by other moving objects. These types of occlusions significantly affect the measurements of the person's position, motion, shape and appearance, posing major challenges to correct tracking and data association. In this paper, we present a method for tracking people in videos based on a simplified part-based model only loosely associated with body parts. Data association is provided by a layered data association approach which performs association at feature, part and global levels in a hierarchical fashion. Occlusions are detected and managed at the part level, with corresponding model update strategies. In addition, the tracker does not make any assumption on the target's motion direction, thus allowing tracking to withstand abrupt sideways movements and changes of directions that frequently occur in busy scenes. Experimental results against popular trackers such as mean shift, particle filters and the recent k-shortest paths (KSP) tracker based on a variety of performance indicators and datasets including ETISEO, AVSS 2007 and PETS 2009 show the effectiveness of the proposed tracker.

show abstract

Section: Model Updatementioning

confidence: 99%

Section: Introduction and Related Workmentioning

confidence: 99%

Tracking people under heavy occlusions by layered data association

Zhang

Perez‐Concha

Piccardi

2014

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…They use human template to find the marching regions in edge map of the inputting image. [27], [28] are based on this method. [28] proposes a direct template matching approach for global shape-based human detection.…”

Section: Related Workmentioning

confidence: 99%

“…[28] proposes a direct template matching approach for global shape-based human detection. [27] is developed form this method and use the hierarchical template to reduce the detection time and solve the occlusion problem to some extent. This method is popular in rigid object detection.…”

Section: Related Workmentioning

confidence: 99%

Accurate Human Detection by Appearance and Motion

Tang

Goto

2010

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn this paper, a human detection method is developed. An appearance based detector and a motion based detector are proposed respectively. A multi scale block histogram of template feature (MB-HOT) is used to detect human by the appearance. It integrates the gray value information and the gradient value information, and represents the relationship of three blocks. Experiment on INRIA dataset shows that this feature is more discriminative than other features, such as histogram of orientation gradient (HOG). A motion based feature is also proposed to capture the relative motion of human body. This feature is calculated in optical flow domain and experimental result in our dataset shows that this feature outperforms other motion based features. The detection responses obtained by two features are combined to reduce the false detection. Graphic process unit (GPU) based implementation is proposed to accelerate the calculation of two features, and make it suitable for real time applications. key words: human detection, multi scale block histogram of template, Graphics process unit

show abstract

“…Recently, part based representations and joint analysis of multiple objects have been adopted to solve partially occluded cases (e.g. Nevatia 2005, 2007c;Shet et al 2007;Lin et al 2007Lin et al , 2004. In these methods, objects are represented as an assembly of several parts.…”

Section: Detection Of Multiple Occluded Objectsmentioning

confidence: 99%

Detection and Segmentation of Multiple, Partially Occluded Objects by Grouping, Merging, Assigning Part Detection Responses

Nevatia

2008

Int J Comput Vis

135

View full text Add to dashboard Cite

We propose a method that detects and segments multiple, partially occluded objects in images. A part hierarchy is defined for the object class. Both the segmentation and detection tasks are formulated as binary classification problem. A whole-object segmentor and several part detectors are learned by boosting local shape feature based weak classifiers. Given a new image, the part detectors are applied to obtain a number of part responses. All the edge pixels in the image that positively contribute to the part responses are extracted. A joint likelihood of multiple objects is defined based on the part detection responses and the object edges. Computation of the joint likelihood includes an inter-object occlusion reasoning that is based on the object silhouettes extracted with the whole-object segmentor. By maximizing the joint likelihood, part detection responses are grouped, merged, and assigned to multiple object hypotheses. The proposed approach is demonstrated with the class of pedestrians. The experimental results show that our method outperforms the previous ones.

show abstract

Hierarchical Part-Template Matching for Human Detection and Segmentation

Cited by 156 publications

References 22 publications

Tracking people under heavy occlusions by layered data association

Tracking people under heavy occlusions by layered data association

Accurate Human Detection by Appearance and Motion

Detection and Segmentation of Multiple, Partially Occluded Objects by Grouping, Merging, Assigning Part Detection Responses

Contact Info

Product

Resources

About