Voting-based simultaneous tracking of multiple video objects

Abstract

A BSTRACTIn the context of content-oriented applications such as video surveillance and video retrieval this paper proposes a stable object tracking method based on both object segmentation and motion estimation. The method focuses on the issues of speed of execution and reliability in the presence of noise, coding artifacts, shadows, occlusion, and object split.Objects are tracked based on the similarity of their features in successive images. This is done in three steps: object segmentation and motion estimation, object matching, and feature monitoring and correction. In the first step, objects are segmented and their spatial and temporal features are computed. In the second step, using a non-linear voting strategy, each object of the previous image is matched with an object of the current image creating a unique correspondence. In the third step, object segmentation errors, such as when objects occlude or split, are detected and corrected. These new data are then used to update the results of previous steps, i.e., object segmentation and motion estimation. The contributions in this paper are the multi-voting strategy and the monitoring and correction of segmentation errors.Extensive experiments on indoor and outdoor video shots containing over 6000 images, including images with multi-object occlusion, noise, and coding artifacts have demonstrated the reliability and real-time response of the proposed method.

High Dimensional versus Low Dimensional Chaos in MPEG-7 Feature Binding for Object Classification

“…Video objects are randomly grouped into different datasets and pre-labeled in four different classes: has person (p), has group of persons (g), has vehicle (v ), and has unknown (u). Abrupt changes in lighting, shaking trees, shadows, and occlusions in any scene may influence the segmentation and tracking of video objects in [11]. To minimize the influence of segmentation, video objects with good and poor segmentation are both mixed together in a class.…”

“…1) to maintain MPEG-7 compliance for video object description, and 2) due to the absence of suitable MPEG-7 motion descriptors, no MPEG-7 motion descriptor is included in the target feature vector. Motion estimation for moving image regions is integrated in tracking [11].…”

novel object detection technique for videos with homogeneous background

“…In supermarkets, the application extends the possibility of counting the products automatically along with the existing video based monitoring system [2]. The steps involved for tracking the objects include preprocessing, feature extraction and Object identification [1]. The pre-processing includes image resizing, image formatting and background modeling.…”

Abnormal Traffic Events Detection Based on Short-time Constant Velocity Model and Spatio-Temporal Trajectory Analysis

“…For event detection, both unsupervised [6] and supervised [7,8] classification methods have been developed. Since unsupervised methods are commonly used to detect anomaly activities instead of some predefined classes of events, supervised anomaly event detection remains prime choice.…”