• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.3
• /
• pp.358-379
• /
• 2010

Multiple object association is an important capability in visual surveillance system with multiple cameras. In this paper, we introduce locally initiating line-based object association with the parallel projection camera model, which can be applicable to the situation without the common (ground) plane. The parallel projection camera model supports the camera movement (i.e. panning, tilting and zooming) by using the simple table based compensation for non-ideal camera parameters. We propose the threshold distance based homographic line generation algorithm. This takes account of uncertain parameters such as transformation error, height uncertainty of objects and synchronization issue between cameras. Thus, the proposed algorithm associates multiple objects on demand in the surveillance system where the camera movement dynamically changes. We verify the proposed method with actual image frames. Finally, we discuss the strategy to improve the association performance by using the temporal and spatial redundancy.

• Journal of Korea Multimedia Society
• /
• v.20 no.6
• /
• pp.893-910
• /
• 2017

In this paper, we propose a simple online multiple object (human) tracking method, LKDeep (Lucas-Kanade feature and Detection based Simple Online Multiple Object Tracker), which can run in fast online enough on CPU core only with acceptable tracking performance for embedded surveillance purpose. The proposed LKDeep is a pragmatic hybrid approach which tracks multiple objects (humans) mainly based on LK features but is compensated by detection on periodic times or on necessity times. Compared to other state-of-the-art multiple object tracking methods based on 'Tracking-By-Detection (TBD)' approach, the proposed LKDeep is faster since it does not have to detect object on every frame and it utilizes simple association rule, but it shows a good object tracking performance. Through experiments in comparison with other multiple object tracking (MOT) methods using the public DPM detector among online state-of-the-art MOT methods reported in MOT challenge [1], it is shown that the proposed simple online MOT method, LKDeep runs faster but with good tracking performance for surveillance purpose. It is further observed through single object tracking (SOT) visual tracker benchmark experiment [2] that LKDeep with an optimized deep learning detector can run in online fast with comparable tracking performance to other state-of-the-art SOT methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.6
• /
• pp.1169-1193
• /
• 2010

In this paper, we present and compare two different multiple camera collaboration strategies to reduce false association in finding the correspondence of objects. Collaboration matrices are defined with the required minimum separation for an effective collaboration because homographic lines for objects association are ineffective with the insufficient separation. The first strategy uses the collaboration matrices to select the best pair out of many cameras having the maximum separation to efficiently collaborate on the object association. The association information in selected cameras is propagated to unselected cameras by the global information constructed from the associated targets. While the first strategy requires the long operation time to achieve the high association rate due to the limited view by the best pair, it reduces the computational cost using homographic lines. The second strategy initiates the collaboration process of objects association for all the pairing cases of cameras regardless of the separation. In each collaboration process, only crossed targets by a transformed homographic line from the other collaborating camera generate homographic lines. While the repetitive association processes improve the association performance, the transformation processes of homographic lines increase exponentially. The proposed methods are evaluated with real video sequences and compared in terms of the computational cost and the association performance. The simulation results demonstrate that the proposed methods effectively reduce the false association rate as compared with basic pair-wise collaboration.

• Journal of Korea Multimedia Society
• /
• v.22 no.2
• /
• pp.167-177
• /
• 2019

Even though so much progresses have been achieved in Multiple Object Tracking (MOT), most of reported MOT methods are not still satisfactory for commercial embedded products like Pan-Tilt-Zoom (PTZ) camera. In this paper, we propose a real-time multiple pedestrians tracking method for embedded environments. First, we design a new light weight convolutional neural network(CNN)-based pedestrian detector, which is constructed to detect even small size pedestrians, as well. For further saving of processing time, the designed detector is applied for every other frame, and Kalman filter is employed to predict pedestrians' positions in frames where the designed CNN-based detector is not applied. The pose orientation information is incorporated to enhance object association for tracking pedestrians without further computational cost. Through experiments on Nvidia's embedded computing board, Jetson TX2, it is verified that the designed pedestrian detector detects even small size pedestrians fast and well, compared to many state-of-the-art detectors, and that the proposed tracking method can track pedestrians in real-time and show accuracy performance comparably to performances of many state-of-the-art tracking methods, which do not target for operation in embedded systems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.6
• /
• pp.2217-2229
• /
• 2015

Since the variations of illumination, the irregular changes of human shapes, and the partial occlusions, multiple person tracking is a challenging work in computer vision. In this paper, we propose a graph clustering method based on spatio-temporal information of moving objects for multiple person tracking. First, the part-based model is utilized to localize individual foreground regions in each frame. Then, we heuristically leverage the spatio-temporal constraints to generate a set of reliable tracklets. Finally, the graph shift method is applied to handle tracklet association problem and consequently generate the completed trajectory for individual object. The extensive comparison experiments demonstrate the superiority of the proposed method.

• The Journal of the Korea Contents Association
• /
• v.7 no.2
• /
• pp.40-50
• /
• 2007

In this paper, we propose an efficient method for detecting and tracking multiple moving objects based on morphological region merging from real-time video sequences. The proposed approach consists of adaptive threshold extraction, morphological region merging and detecting and tracking of objects. Firstly, input frame is separated into moving regions and static regions using the difference of images between two consecutive frames. Secondly, objects are segmented with a reference background image and adaptive threshold values, then, the segmentation result is refined by morphological region merge algorithm. Lastly, each object segmented in a previous step is assigned a consistent identification over time, based on its spatio-temporal information. The experimental results show that a proposed method is efficient and useful in terms of real-time multiple objects detecting and tracking.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.6
• /
• pp.1263-1268
• /
• 2018

In this paper, a video analysis is proposed to implement video surveillance system with deep learning object detection and probabilistic data association filter for tracking multiple objects, and suggests its implementation using GPU. The proposed video analysis technique involves object detection and object tracking sequentially. The deep learning network architecture uses ResNet for object detection and applies probabilistic data association filter for multiple objects tracking. The proposed video analysis technique can be used to detect intruders illegally trespassing any restricted area or to count the number of people entering a specified area. As a results of simulations and experiments, 48 channels of videos can be analyzed at a speed of about 27 fps and real-time video analysis is possible through RTSP protocol.

• Journal of the Society of Naval Architects of Korea
• /
• v.60 no.4
• /
• pp.248-255
• /
• 2023

In order to implement the autonomous navigation function, it is essential to track an object within a certain radius of the ship's route. This paper proposes the Multiple Probabilistic Data Association Filter (MPDAF), which can track multiple ships by extending Probabilistic Data Association Filter (PDAF), an existing single object tracking algorithm, using radar data obtained from real marine environments. The proposed MPDAF algorithm was developed to address the problem of tracking multiple objects in a complex environment where there can be significant uncertainty in the number and identification of objects to be tracked. Using real-world radar data provided by the German aerospace center (DLR), it has been verified that the proposed algorithm can track a large number of objects with a small position error.

• ETRI Journal
• /
• v.37 no.3
• /
• pp.551-561
• /
• 2015

We propose a novel multiple-object tracking algorithm for real-time intelligent video surveillance. We adopt particle filtering as our tracking framework. Background modeling and subtraction are used to generate a region of interest. A two-step pedestrian detection is employed to reduce the computation time of the algorithm, and an iterative particle repropagation method is proposed to enhance its tracking accuracy. A matching score for greedy data association is proposed to assign the detection results of the two-step pedestrian detector to trackers. Various experimental results demonstrate that the proposed algorithm tracks multiple objects accurately and precisely in real time.

• The Journal of Information Systems
• /
• v.3
• /
• pp.71-82
• /
• 1994

Knowledge acquisition, maintenance of knowledge base, and validation and verification of knowledge are the addressed bottlenecks of building successful knowledge based systems. Along with the increment of interesting in the knowledge based systems, the organization needs to develop a new one although it has a similar one. This causes several serious problems including knowledge redundancy and maintenance of knowledge base. This paper present three models of the reusable knowledge base which might be the solution to the above problem. Three models are : 1) multiple knowledge bases for a single AI application, 2) multiple knowledge bases for multiple AI applications, 3) a single knowledge base for multiple AI applications. A new approach to build such a reusable knowledge base in a homogeneous environment is presented. Our model combines the essential object-oriented techniques with rules in a consistent manner. Important aspects of applying object-oriented techniques to AI are discussed (inheritance, encapsulation, message passing), and some potential problems in building an AI application (decomposition technique of knowledge, search time, and heterogeneous environment) are pointed out. The models of a reusable knowledge base provide several amenities : 1) reduce the knowledge redundancy, 2) reduce the effort of maintenance of the knowledge base, 3) reuse the resource of the multiple domain knowledge bases, 4) reduce the development time.