Qi Tian

An Efficient Sequential Approach to Tracking Multiple Objects Through Crowds for Real-Time Intelligent CCTV Systems

Efficiency and robustness are the two most important issues for multiobject tracking algorithms in real-time intelligent video surveillance systems. We propose a novel 2.5-D approach to real-time multiobject tracking in crowds, which is formulated as a maximum a posteriori estimation problem and is approximated through an assignment step and a location step. Observing that the occluding object is usually less affected by the occluded objects, sequential solutions for the assignment and the location are derived. A novel dominant color histogram (DCH) is proposed as an efficient object model. The DCH can be regarded as a generalized color histogram, where dominant colors are selected based on a given distance measure. Comparing with conventional color histograms, the DCH only requires a few color components (31 on average). Furthermore, our theoretical analysis and evaluation on real data have shown that DCHs are robust to illumination changes. Using the DCH, efficient implementations of sequential solutions for the assignment and location steps are proposed. The assignment step includes the estimation of the depth order for the objects in a dispersing group, one-by-one assignment, and feature exclusion from the group representation. The location step includes the depth-order estimation for the objects in a new group, the two-phase mean-shift location, and the exclusion of tracked objects from the new position in the group. Multiobject tracking results and evaluation from public data sets are presented. Experiments on image sequences captured from crowded public environments have shown good tracking results, where about 90% of the objects have been successfully tracked with the correct identification numbers by the proposed method. Our results and evaluation have indicated that the method is efficient and robust for tracking multiple objects ( ges 3) in complex occlusion for real-world surveillance scenarios.

Principal color representation for tracking persons

This paper proposes a novel method for tracking persons based on the principal colors of human objects. First, an efficient human object representation method, principal color representation (PCR), is proposed. Asymmetric similarity measures are then proposed based on the principal color representation. These asymmetric similarity measures could be used to evaluate the matching between two individuals as well as visual evident of an individual in a group. An efficient algorithm for tracking persons as individuals or in groups is then described. The method has been tested using image sequences containing multiple moving persons frequently gathering and separating. Our test results have shown that proposed method has successfully tracked both persons as individuals or in groups, and is robust to illumination changes.

Adaptive background subtraction based on feedback from fuzzy classification

Background subtraction is an important issue for achieving effective foreground object detection in video surveillance. Background subtraction requires the timely updating of a background model to gradual illumination changes as well as the significant changes in the background. It is also essential that foreground objects have little impact on the updating of the background. Based on our change-type categories, we propose an adaptive background subtraction method where a two-strategy-based background maintenance is introduced to adapt to different types of changes by using feedback from change segmentation and region classification. The work mainly contributes to the following issues: 1. propose a change segmentation method that detects change regions as well as provides spatiotemporal information about the changes by using fuzzy techniques; 2. propose a fuzzy reasoning method to classify background and foreground changes at the object level; and 3. propose a new method for adaptive background maintenance based on the feedback from pixel-level to object-level processing that is able to avoid tradeoff in the updating rate. Experiments on indoor and outdoor video scenes are conducted and results show that the proposed method adapts well to various background changes without absorbing foreground objects. Comparisons with an existing method using a constant learning rate show an improved performance.

An adaptive enhanced focusing technique for whole slide imaging using contextual information

Optical imaging systems especially microscopy systems under higher magnifications often have relatively limited depth of field. This constraint results in partial focusing in the image. To overcome this partial focusing problem, enhanced focusing (EF) techniques are introduced to generate all-well-focused images. A sequence of images for each field is acquired at the same image field and along the same optical axis at different acquisition depths. The images are partitioned into tiles where the best focused sub-images for each tile among the sequence is found. The final image is the mosaicking of the found sub-images. Whole slide imaging (WSI) is an emerging imaging technology since the mid-1990s. It automatically acquires digital images from a biomedical slide field by field using robotic microscopic devices at high resolution and then stitches them together to form a large-dimensional high- resolution montage. Each field is just a small window of the large scene of the slide. In the context of WSI, all fields are to be focused and such an EF-WSI procedure could be very slow. In this work, we have proposed a new adaptive focusing method using contextual information in the slide for EF-WSI. We can reduce about 1/3 of computation time while maintaining good image quality.