In 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.

In real-time content-oriented video applications, fast unsupervised object segmentation is required. This paper proposes a real-time unsupervised object segmentation that is stable throughout large video shots. It trades precise segmentation at object boundaries for speed of execution and reliability in varying image conditions. This interpretation is most appropriate to applications such as surveillance and video retrieval where speed and temporal reliability are of more concern than accurate object boundaries. Both objective and subjective evaluations, and comparisons to other methods show the robustness of the proposed methods while being of reduced complexity. The proposed algorithm needs on average 0.15 seconds per image. The proposed segmentation consists of four steps: motion detection, morphological edge detection, contour analysis, and object labeling. The contributions in this paper are: a segmentation process of simple but effective tasks avoiding complex operations, a reliable memory-based noise-adaptive motion detection, and a memorybased contour tracing and analysis method. The proposed contour tracing aims 1) at finding contours with complex structure such as those containing dead or inner branches and 2) at spatial and temporal adaptive selection of contours. The motion detection is spatio-temporal adaptive as it uses estimated intra-image noise variance and detected inter-image motion.

This paper presents a simplification and merging technique based on an initial region partition of color images: a Region Adjacency Graph (RAG). We propose a general scheme that can be employed for both color image simplification and/or segmentation. A new filtering algorithm of RAG is presented and included within a merging algorithm. The region models associated to each node are simplified and morover the RAG is simplified by merging similar nodes.

A hybrid segmentation method for color images is presented in this work. It combines 2D histogram clustering to produce segmentation maps fused together providing an initial unsupervised clustering of the dominant colors of the image. Region information is then used and a novel technique is introduced to simplify the Region Adjacency Graph by merging candidate regions until the stabilization of a "good" segmentation criterion. Merged regions are refined by a color watershed using local and global properties of the image. The robustness of the method is experimentally verified and the color space influence is studied.