Fence Climbing Action Recognition Dataset

The current security industry faces challenges from people climbing over walls, fences, and other security hazards. Traditional surveillance methods often cannot timely and effectively recognize these abnormal behaviors. Existing solutions are insufficient in the accuracy and real-time detection of actions, resulting in the inability to quickly respond to potential dangers. This dataset aims to support the training of action recognition models by providing high-quality video data, enhancing the ability of surveillance systems to identify abnormal behaviors. Video data is collected using high-definition cameras in surveillance scenarios, covering different lighting and weather conditions to ensure diversity and authenticity. Each video undergoes multiple rounds of annotation and consistency checks, finally reviewed by security domain experts to ensure the accuracy and consistency of the annotations. The data storage format is MP4, organized in chronological order, facilitating subsequent processing and analysis. The core advantage of this dataset is its high annotation accuracy (over 95%), combined with innovative data augmentation techniques such as random cropping and color variation to enhance model generalization. Meanwhile, the dataset can significantly improve the performance metrics of abnormal behavior detection, with an expected detection rate improvement of up to 20%, effectively reducing the false alarm rate.