Pedestrian detection using wavelet templates

Oren, Michael B.; Papageorgiou, C.; Sinha, Pavel; Osuna, E.; Poggio, Tomaso

doi:10.1109/cvpr.1997.609319

Cited by 530 publications

(273 citation statements)

References 11 publications

Supporting

Mentioning

265

Contrasting

Unclassified

Order By: Relevance

“…For identifying pedestrians in a single image, [29] used wavelets to learn a characteristic pedestrian template and employed support vector machines for classification. In [18], a hierarchical coarse-to-fine template approach with edge maps was used to detect pedestrians.…”

Section: Related Work On Action Recognitionmentioning

confidence: 99%

Minimal-latency human action recognition using reliable-inference

Davis

Tyagi

2006

Image and Vision Computing

View full text Add to dashboard Cite

We present a probabilistic reliable-inference framework to address the issue of rapid detection of human actions with low error rates. The approach determines the shortest video exposures needed for low-latency recognition by sequentially evaluating a series of posterior ratios for different action classes. If a subsequence is deemed unreliable or confusing, additional video frames are incorporated until a reliable classification to a particular action can be made. Results are presented for multiple action classes and subsequence durations, and are compared to alternative probabilistic approaches. The framework provides a means to accurately classify human actions using the least amount of temporal information. q

show abstract

Section: Related Work On Action Recognitionmentioning

confidence: 99%

Minimal-latency human action recognition using reliable-inference

Davis

Tyagi

2006

Image and Vision Computing

View full text Add to dashboard Cite

show abstract

“…Several different image processing methods and systems have been developed in the last years, including shape-based methods [5,6], textureand template-based methods [7,8], stereo [9], as well as motion clues [10,11]. All these methods have to overcome the difficulties of different appearances of pedestrians in the visual domain caused mainly by e.g.…”

Section: Introductionmentioning

confidence: 99%

IR Pedestrian Detection for Advanced Driver Assistance Systems

Bertozzi

Broggi

Carletti

et al. 2003

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This paper describes a system for pedestrian detection in infrared images implemented and tested on an experimental vehicle. A specific stabilization procedure is applied after image acquisition and before processing to cope with vehicle movements affecting the camera calibration. The localization of pedestrians is based on the search for warm symmetrical objects with specific size and aspect ratio. A set of filters is used to reduce false detections. The final validation process relies on the human shape's morphological characteristics.

show abstract

“…This paper describes an attempt to take advantage of such novel features. To illustrate our approach, we focus on the detection of human bodies in a video stream, like in [8,9]. Basically, we apply machine learning algorithms on the rectangles of a silhouette to decide, in real-time, whether this silhouette corresponds to that of a learned instance of a human silhouette.…”

Section: Introductionmentioning

confidence: 99%

Robust Analysis of Silhouettes by Morphological Size Distributions

Barnich

Jodogne

Droogenbroeck

2006

Advanced Concepts for Intelligent Vision Systems

View full text Add to dashboard Cite

Abstract. We address the topic of real-time analysis and recognition of silhouettes. The method that we propose first produces object features obtained by a new type of morphological operators, which can be seen as an extension of existing granulometric filters, and then insert them into a tailored classification scheme. Intuitively, given a binary segmented image, our operator produces the set of all the largest rectangles that can be wedged inside any connected component of the image. The later are obtained by a standard background subtraction technique and morphological filtering. To classify connected components into one of the known object categories, the rectangles of a connected component are submitted to a machine learning algorithm called EXtremely RAndomized trees (Extra-trees). The machine learning algorithm is fed with a static database of silhouettes that contains both positive and negative instances. The whole process, including image processing and rectangle classification, is carried out in real-time. Finally we evaluate our approach on one of today's hot topic: the detection of human silhouettes. We discuss experimental results and show that our method is stable and computationally effective. Therefore, we assess that algorithms like ours introduce new ways for the detection of human in video sequences.

show abstract

Pedestrian detection using wavelet templates

Cited by 530 publications

References 11 publications

Minimal-latency human action recognition using reliable-inference

Minimal-latency human action recognition using reliable-inference

IR Pedestrian Detection for Advanced Driver Assistance Systems

Robust Analysis of Silhouettes by Morphological Size Distributions

Contact Info

Product

Resources

About