ABANDONED OBJECT DETECTION VIA TEMPORAL CONSISTENCY MODELING AND BACK TRACING VERIFICATION FOR VISUAL SURVEILLANCE THROUGH IOT
Abstract : This paper presents an effective approach for detecting abandoned luggage in surveillance videos. We combine short- and long-term background models to extract foreground objects, where each pixel in an input image is classified as a 2-bit code. Subsequently, we introduce a framework to identify static foreground regions based on the temporal transition of code patterns, and to determine whether the candidate regions contain abandoned objects by analyzing the back-traced trajectories of luggage owners. The experimental results obtained based on video images from 2006 Performance Evaluation of Tracking and Surveillance and 2007 Advanced Video and Signal-based Surveillance databases show that the proposed approach is effective for detecting abandoned luggage, and that it outperforms previous methods.
• With existing surveillance systems, the cause of any incident is determined after it has happened.
• Security personnel analyze the captured videos for suspicious activities/objects which is a passive approach.
• There is a need of an active surveillance mechanism to enhance the safety of persons/objects in public places by detecting potential suspicious situation and generating automatic alerts
• accordingly.
• A significant challenge in the object detection technique is to segregate an abandoned or intentionally left object from several other objects that exist in the scene.
• When a person leaves a bag or any similar object at any place, proposed system analyzes it, determines the most likely position of the object and detects it as unattended.
• In the proposed approach, foreground objects are extracted by background subtraction method.
• In the visual surveillance research, detecting abandoned luggage is referred to as the problem of abandoned-object or left-luggage detection.
• To address this problem, foreground/background extraction techniques are suitable for identifying static foregrounds regions (i.e., objects that remain static for a long time) as left-luggage candidates.
• All methods attain high recall values; thus, reducing the occurrence of false alarms (i.e., improving the precision) is a critical problem.
• The challenge of the 11th video is caused by the crowded scene and partial occlusion problem of small objects.
• In order to overcome the security issues, there is the need for automated surveillance systems probably in the public places.
• The proposed machine model addresses the abandoned object in an image through the extraction of foregrounds and Stationary foregrounds for the real-time monitoring systems.
• In this paper, we proposed a reliable algorithm to detect motion and find humans in the surveillance video stream and identify the left luggage.
• Detecting the new objects in the image scene is an important step in the proposed technique. First, the proposed method learns the background from the initial frames later it checks the presence of the new objects using the frame differencing technique.
• With the tracking and detection of the new objects, the proposed method also computes the position of the detected objects, the method also stores or save the object position.
• We proposed a framework to detect the abandoned luggage in the public area. The proposed system is efficient to work in the presence of occlusion, noise, and affine distortion.
• In this paper, we propose using temporal-continuity information to improve the performance.
• To the frame-by-frame tracking approaches such as the KF- or UKF employed in, our approach is superior in handling temporary occlusions and is still highly efficient to implement.
• We then employ the Bhattacharyya coefficient to identify the blob with the color distribution most similar to that of the owner in W1, and then create a window W2 centered at the newly identified blob.
• It is adequately efficient when tracking the owner by using a simple blob tracker with a human-detector verification method in a spatial-temporal window search.
• This will help to remove the noise in video frames to avoid false detection and improve the performance of the algorithm.
|