Moving object detection and classification in surveillance systems using moving cameras
Communications Faculty of Sciences University of Ankara Series A2-A3 …, 2018•dergipark.org.tr
In this paper, wepresent a novel method to detect and classify moving objects from
surveillancevideos that are obtained from a moving camera. In our method, we first
estimatethe camera motion by interpreting the movement of interest points in the scene.
Then, we eliminate the camera motion and find candidate regions that belong tothe moving
objects. Considering these regions as priors, we apply an efficientsegmentation algorithm to
obtain accurate object boundaries for the movingobjects. Finally, we classify the detected …
surveillancevideos that are obtained from a moving camera. In our method, we first
estimatethe camera motion by interpreting the movement of interest points in the scene.
Then, we eliminate the camera motion and find candidate regions that belong tothe moving
objects. Considering these regions as priors, we apply an efficientsegmentation algorithm to
obtain accurate object boundaries for the movingobjects. Finally, we classify the detected …
In this paper, wepresent a novel method to detect and classify moving objects from surveillancevideos that are obtained from a moving camera. In our method, we first estimatethe camera motion by interpreting the movement of interest points in the scene.Then, we eliminate the camera motion and find candidate regions that belong tothe moving objects. Considering these regions as priors, we apply an efficientsegmentation algorithm to obtain accurate object boundaries for the movingobjects. Finally, we classify the detected objects as people, vehicle, orothers using some morphological features and the velocity vectors of movingobjects. The evaluation of the proposed approach on our surveillance datasetshows that our approach is very effective for determining the classes of movingobjects in a moving camera setting.
dergipark.org.tr
以上显示的是最相近的搜索结果。 查看全部搜索结果