Vehicle theft recognition from surveillance video based on spatiotemporal attention
- PDF / 1,393,842 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 73 Downloads / 196 Views
Vehicle theft recognition from surveillance video based on spatiotemporal attention Lijun He 1 & Shuai Wen 1 & Liejun Wang 2 & Fan Li 1 Accepted: 7 September 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Frequent vehicle thefts have a highly detrimental impact on public safety. Thanks to surveillance equipment distributed throughout a city, a large number of videos that can be used to recognize vehicle theft are available. However, vehicle theft behavior has the characteristics of a small criminal target and small movement. Hence, the existing action recognition algorithms cannot be directly applied for the recognition of vehicle theft. In this paper, we propose a method for vehicle theft recognition based on a spatiotemporal attention mechanism. First, a database of vehicle theft is established by collecting videos from the Internet and an existing dataset. Then, we establish a vehicle theft recognition network and introduce a spatiotemporal attention mechanism for application when extracting the spatiotemporal features of theft. Through the learning of adaptive feature weights, the features that contribute most greatly to recognition are emphasized. Simulation experiments show that our proposed algorithm can achieve 97.04% accuracy on the collected vehicle theft database. Keywords Vehicle theft recognition . Surveillance video . Spatiotemporal attention
1 Introduction With the rapid development of the economy and the improvement of people’s living standards, vehicles such as motorcycles and automobiles have become important modes of travel. However, the increasing popularity of vehicles is also accompanied by an increase in vehicle theft. In most countries and regions, a large number of vehicles, vehicle contents and vehicle components are stolen every year. Vehicle theft is an abnormal behavior that occurs frequently in daily life and results in enormous losses to people’s property and threats to public safety. Therefore, recognizing vehicle theft timely is of great significance for ensuring public safety. Fortunately, since every corner of a city is covered with surveillance equipment to ensure public safety, a large amount of surveillance video data is generated. Therefore, it is worthy studying vehicle theft recognition from large amount of surveillance videos.
* Fan Li [email protected] 1
School of Information and Communications Engineering, Xi’an Jiaotong University, Xi’an 710049, China
2
College of Information Science and Engineering, Xinjiang University, Urumqi 830046, China
Vehicle theft recognition belongs to the category of action recognition. In recent years, action recognition has been a popular topic of research, and great progress has been achieved. Action recognition methods can be divided into two categories: recognition based on traditional manual features and that based on deep learning. In the recognition method based on traditional manual features, it is necessary to sample the video, extract features from the samples, encode the extracted manu
Data Loading...
