Robust event detection by radial reach filter (RRF)

Satoh, Yutaka; Tanahashi, Hideki; Wang, Caihua; Kaneko, Sadahiro; Niwa, Yasumasa; Yamamoto, Kazuhiko

doi:10.1109/icpr.2002.1048379

Cited by 21 publications

(10 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) Real-time detection and refinement of human areas can be realized due to the high efficiency of the CENTRIST feature [4], and by detecting humans and computing an integral image only on the foreground extracted by the Radial Reach Filter (RRF) [6].…”

Section: Basic Ideasmentioning

confidence: 99%

“…1. First, RRF [6] is utilized to extract the foreground of each frame from an indoor video, which can detect new objects in a time-series image even if they stop moving after they enter the scene. Next, the CENTRIST feature [4] is applied to detect humans only in the foreground regions of each frame, to improve the computational efficiency.…”

Section: Basic Ideasmentioning

confidence: 99%

“…In order to estimate foot position, a coarse foot position estimation scheme is proposed based on background subtraction by RRF [6], human detection by the CENTRIST feature [4], and projection and back-projection by direct linear transformation (DLT) [13], as depicted in Fig. 2.…”

Section: Coarse Foot Position Estimationmentioning

confidence: 99%

See 2 more Smart Citations

Human Area Refinement for Human Detection

Ueno

Kobayashi

et al. 2015

Image Analysis and Processing — ICIAP 2015

View full text Add to dashboard Cite

Abstract. Human detection technologies are very useful tools to understand human activity for various purposes, such as surveillance. Recently, trackingby-detection methods have also become popular for analyzing human activity, but their performance is greatly affected by the accuracy of detected human areas because they use online learning based on the detected results. In order to improve the performance of such tracking methods, the inclination of human bodies in the image is considered as a way to refine the detected human bounding boxes. Based on background subtraction and a novel scheme of estimating human foot position, a refinement scheme is proposed to estimate a bounding box more accurately, which can better fit the contours of inclined human bodies than the conventional method. Experimental results illustrated that the bounding boxes refined by the proposed algorithm achieved a higher cover rate of 92.7 % and a smaller mean angle error of 0.7° compared with the cover rate of 83.7 % and mean angle error of 3.8° obtained using the conventional method, as determined by comparison with the ground truth, and a real-time detection speed of 32.3 fps on a 640 × 480 video has been realized. Thus, tracking performance is significantly enhanced by refining the human areas, with a mean improvement of 42.4 % in the F-measure when compared with the conventional method. [3], and the CENTRIST feature [4]. The effectiveness of these methods has been proven in practice for the detection of upright complete humans. With the development of human detection technologies, an approach called tracking-by-detection [5] has become popular recently. This approach treats the tracking problem as a detection task applied over time. Such a method learns classifiers for tracking online using detected Human Area Refinement for Human Detection 131 human bounding boxes (b-boxes) instead of using offline labeled data for training, and thus the quality of the classifiers is greatly affected by the accuracy of the detected human areas, which contributes to the final tracking performance.Although most detection methods can provide a high detection rate, accurate depiction of human postures and regions still cannot be achieved, i.e., all existing methods can only detect approximate human locations denoted by upright b-boxes, and cannot deal with the contour of an inclined human body very well. In order to improve the accuracy of the detected human areas, in this paper we propose a refinement algorithm for the detected human bounding box (b-box) to fit the contour of the inclined human body based on background subtraction, human detection, and a novel scheme of estimating human head and foot position using a predefined human height.The rest of this paper is organized as follows. Section 2 briefly introduces related work. Section 3 describes the details of the proposed approach. Section 4 presents the experimental results and discussion, and Section 5 concludes the paper. In addition, real-time detection has attracted more and more attention,...

show abstract

Section: Basic Ideasmentioning

confidence: 99%

Section: Basic Ideasmentioning

confidence: 99%

See 1 more Smart Citation

Human Area Refinement for Human Detection

Ueno

Kobayashi

et al. 2015

Image Analysis and Processing — ICIAP 2015

View full text Add to dashboard Cite

show abstract

“…The first one is Normalized Vector Distance (NVD), for detecting differences in color, and the second one is Radial Reach Filter (RRF) [3], for detecting differences in texture. NVD is calculated as,…”

Section: Image Subtractionmentioning

confidence: 99%

<b>Frontal Obstacle Detection Using Background Subtraction and Frame Registration</b>

Nakasone¹,

Nagamine²,

Ukai³

et al. 2017

Q. rep. RTRI

View full text Add to dashboard Cite

show abstract

“…Moreover, these techniques cannot cope with natural movements of the background, changing in the background geometry, or camera oscillations, resulting again in the generation of a great amount of false alarms. A partial solution to the issues raised by the previous discussion is given by the Radial Reach Filter algorithm (Satoh et al, 2002), where the thresholding operations to discern between background and foreground in the image are performed at pixel level, but taking into account a sort of local texture. One main concern remains: The fact that the threshold values are commonly chosen by the operator, implies that the performance of the algorithm is depending on the operator experience and skills.…”

Section: State Of the Artmentioning

confidence: 99%

BUILDING A NORMALITY SPACE OF EVENTS - A PCA Approach to Event Detection

Cenedese

Frezza

Campana³

et al. 2008

Proceedings of the Third International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

Abstract:The detection of events in video streams is a central task in the automatic vision paradigm, and spans heterogeneous fields of application from the surveillance of the environment, to the analysis of scientific data. Actually, although well captured by intuition, the definition itself of event is somewhat hazy and depending on the specific application of interest. In this work, the approach to the problem of event detection is different in nature. Instead of defining the event and searching for it within the data, a normality space of the scene is built from a chosen learning sequence The event detection algorithm works by projecting any newly acquired image onto the normality space so as to calculate a distance from it that represents the innovation of the new frame, and defines the metric for triggering an event alert.

show abstract

Robust event detection by radial reach filter (RRF)

Cited by 21 publications

References 5 publications

Human Area Refinement for Human Detection

Human Area Refinement for Human Detection

<b>Frontal Obstacle Detection Using Background Subtraction and Frame Registration</b>

BUILDING A NORMALITY SPACE OF EVENTS - A PCA Approach to Event Detection

Contact Info

Product

Resources

About