Basketball court detection is the key step of video annotation, however the court present different color when using different camera or in different play court. In this paper the adaptive Gaussian Mixture Model (GMM) is used to build the model of the basketball court, which is used in the basketball video annotation. The proposed algorithm extracts the main color of the court's main color ...
Basketball court detection is the key step of video annotation, however the court present different color when using different camera or in different play court. In this paper the adaptive Gaussian Mixture Model (GMM) is used to build the model of the basketball court, which is used in the basketball video annotation.
More Basketball Court Detection images
This paper presents us with a framework for the automatic player position detection (APPD) in the game of basketball. Court players are detected in the images broadcasted via television stations. In them, at any point of time, the view is from only one camera. This makes the detection process much more difficult.
Our proposal to track players in a basketball game is based on a tracking-by-detection approach as seen in Figure 2: First, the different individuals on the court are detected in every frame and then, matches are established along time. Given a video of a basketball game, the prior that players are inside the court along the sequence is used to restrict the area where players should be searched, thus avoiding the detection of spectators or bench players.
Basketball court detection (with too many lines) will be very difficult to identify using above strategies. Binary segmentation using auto encoders An auto encoder for sports field segmentation will be required as explained in the Classification of Actions by Simone Francia (see section 3.2.2 : Auto encoder model of the basketball court)
Does Salient Object Detection can be used to segment out the basketball court in the videos? Or is there any other better method for it? I do not plan to use conventional method because I want to segment the court even if the videos are taken with arbitrary camera angle.
typically found in basketball courts, will not be detected as often as if an entire frame were used. The color detector performs detection by using thresholds in the HSV space. The choice of the HSV space as oppose to RGB was motivated by the fact that the HSV enables higher discrimination between changes in color rather than saturation and brightness.
For object detection with images, navigate to your directory on the command line and run: python detect.py --images <FILEPATH> I decided it would be useful to have an implementation available in a Jupyter notebook to allow for easier experiementation.
Each line is an individual frame and contains the centerpoint coordinates of the highest scoring basketball detected as well as the radius and "free" column All frames are represented exactly once The free column is True if the highest scoring basketballs bounding box has no overlap with the highest scoring persons bounding box