Semi-supervised Learning on Real-time Pedestrian Detection System
نویسندگان
چکیده
This research proposed a pedestrian detection system in an outdoor scene by a pin-hole camera with field-programmable gate array. We used two different feature descriptors included histograms of oriented gradients and local weighted pattern which were descripted the shape and textural information for the image feature of pedestrians. Semi-supervised learning with linear support vector machine would be used as the classifier to detect pedestrians. A car to vulnerable road users both adult and child scenarios were selected, and the maximum test speed of demonstrated vehicle was 30 km/h. The average detection rates of our proposed system for both scenarios were 100% and 96.67%, respectively.
منابع مشابه
Efficient Labelling of Pedestrian Supervisions
Object detection is a fundamental goal to achieve intelligent visual perception by computers due to the fact that objects are the basic building blocks to achieve higher level image understanding. Among the numerous categories of objects in the real-world, pedestrians are among the most important due to several potential benefits brought about by successful pedestrian detection. Often, pedestri...
متن کاملAutomatic Process to Build a Contextualized Detector
This article tackles the real-time pedestrian detection problem using a stationary uncalibrated camera. More precisely we try to specialize a classi er by taking into account the context of the scene. To achieve this goal, we introduce an o ine semi-supervised approach which uses an oracle. This latter must automatically label a video, in order to obtain contextualized training data. The propos...
متن کاملMonocular Camera Fall Detection System Exploiting 3D Measures: A Semi-supervised Learning Approach
Falls have been reported as the leading cause of injury-related visits to emergency departments and the primary etiology of accidental deaths in elderly. The system presented in this article addresses the fall detection problem through visual cues. The proposed methodology utilize a fast, real-time background subtraction algorithm based on motion information in the scene and capable to operate ...
متن کاملIdentification and Prediction of Large Pedestrian Flow in Urban Areas Based on a Hybrid Detection Approach
Recently, population density has grown quickly with the increasing acceleration of urbanization. At the same time, overcrowded situations are more likely to occur in populous urban areas, increasing the risk of accidents. This paper proposes a synthetic approach to recognize and identify the large pedestrian flow. In particular, a hybrid pedestrian flow detection model was constructed by analyz...
متن کاملSemi-supervised Elastic net for pedestrian counting
Pedestrian counting plays an important role in public safety and intelligent transportation. Most pedestrian counting algorithms based on supervised learning require much labeling work and rarely exploit the topological information of unlabelled data in a video. In this paper, we propose a SemiSupervised Elastic Net (SSEN) regressionmethod by utilizing sequential information between unlabelled ...
متن کامل