Last update:
7/16/2005
Multimedia Analysis
Object detection and tracking
Playfield plays the fundamental role in automatically analyzing many sports programs. Many semantic clues could be inferred from the results of playfield segmentation. A novel playfield segmentation method based on Gaussian mixture models (GMMs) is proposed. Firstly, training pixels are automatically sampled from frames. Then, by supposing that field pixels are the dominant components in most of the video frames, we build the GMMs of the field pixels and use these models to detect playfield pixels. Finally region-growing operation is employed to segment the playfield regions from the background.
Text in images and video frames carries important information for sports video understanding and retrieval. By using multiscale wavelet features, we propose a novel coarse-to-fine algorithm that is able to locate text lines even under complex background. First, in the coarse detection, after the wavelet energy feature is calculated to locate all possible text pixels, a density-based region growing method is developed to connect these pixels into regions which are further separated into candidate text lines by structural information. Secondly, in the fine detection, with four kinds of texture features extracted to represent the texture pattern of a text line, a forward search algorithm is applied to select the most effective features. Finally, an SVM classifier is used to identify true text from the candidates based on the selected features.
After the playfield detection procedure, assuming players are always located within the area of playfield, the non-playfield regions surrounded by playfield region are identified as player regions.
In the tracking procedure, improved particle filter is proposed to reduce the sample set. The size of the sample set utilized by particle filter is directly related to the computational cost and should be kept as small as possible to improve the efficiency of particle filter. A simple but effective sample re-weighting scheme based on support vector regression (SVR) is adopted here to tackle this problem. Then, automatic object detection is combined into the improved particle filter framework to segment the players and ball in soccer video as the initialization of tracker. Thus we integrate different object tracking into one uniform particle filter framework to reduce the complexity of the tracking system. Finally, the tracking result is extended to supply strong applications for sports video semantic analysis and enrichment.
In ball detection procedure, ball candidates are first extracted from several consecutive frames using color, shape, and size cues. Then a weighted graph is established, with each node representing a candidate and each edge linking two candidates in adjacent frames. Finally, Viterbi algorithm is applied to extract the optimal path as ball’s locations. In ball tracking procedure, Kalman filter based template matching is utilized to track the ball in subsequent frames. Kalman filter and the template are initialized using detection results. In each tracking step, ball location is verified to update the template and guide possible ball re-detection.
Athlete identification is important for sport video content analysis since users often care about the video clips with their preferred athletes. We propose a method for athlete identification by combing the segmentation, tracking and recognition procedures into a coarse-to-fine scheme for jersey number (digital characters on sport shirt) detection. image segmentation is first employed to separate the jersey number regions with its background. And size/pipe-like attributes of digital characters are used to filter out candidates. Then, a K-NN (K nearest neighbor) classifier is employed to classify a candidate into a digit in “0-9” or negative. In the recognition procedure, we use the Zernike moment features, which are invariant to rotation and scale for digital shape recognition. After tracking tens of frames, the overall recognition results are combined to determine if a candidate is a true jersey number or not by a voting procedure.
