Robust multiple target tracking under occlusion using fragmented mean shift and Kalman filter
- Gargi phadke
- 2011 International Conference on Communications…
Fig. 1 Flowchart of the proposed approach for tracing multi-person The majority of conventional video tracking surveillance systems assumes a likeness to a person’s appearance for some time, and individuality of the person during tracking. However, illumination changes by weather or lighting and occlusions by overlapping people make tracking difficult. To address this situation, we use an adaptive noise, background, and human body model updated statistically frame-by-frame, and correctly construct a person with body parts. Each incoming frame image is corrected to remove shadows by illumination changes and to make a noise image. The corrected image is subtracted by a background model to detect persons. The detected persons are formed by a human body model. The formed person is labeled and recorded in a person’s list, which stores the individual’s human body model details. Such recorded information can be used to identify tracked persons. The results of this experiment are demonstrated in several indoor situations.