Fast action recognition using negative space features
作者：
Highlights：
• A novel action descriptor is proposed by using novel feature extraction techniques.
• A novel fish action dataset is introduced to test effectiveness for animal actions.
• The proposed system has highest accuracy with lowest processing time.
• Robust to viewpoint, shadow, occlusion, corrupted-image and low frame rate.
• Unlike other methods, proposed system computes action cycle length automatically.
摘要
•A novel action descriptor is proposed by using novel feature extraction techniques.•A novel fish action dataset is introduced to test effectiveness for animal actions.•The proposed system has highest accuracy with lowest processing time.•Robust to viewpoint, shadow, occlusion, corrupted-image and low frame rate.•Unlike other methods, proposed system computes action cycle length automatically.
论文关键词：Action recognition,Negative space action descriptors,Silhouette,Fuzzy membership,Implicit method,Cycle length,Fish actions
论文评审过程：Available online 7 August 2013.
论文官网地址：https://doi.org/10.1016/j.eswa.2013.07.082
