Abstract
In this paper, we address the generation of semantic labels describing the headgear accessories carried out by people in a scene under surveillance, only using depth information obtained from a Time-of-Flight (ToF) camera placed in an overhead position. We propose a new method for headgear accessories classification based on the design of a robust processing strategy that includes the estimation of a meaningful feature vector that provides the relevant information about the people’s head and shoulder areas. This paper includes a detailed description of the proposed algorithmic approach, and the results obtained in tests with persons with and without headgear accessories, and with different types of hats and caps. In order to evaluate the proposal, a wide experimental validation has been carried out on a fully labeled database (that has been made available to the scientific community), including a broad variety of people and headgear accessories. For the validation, three different levels of detail have been defined, considering a different number of classes: the first level only includes two classes (hat/cap, and no hat/cap), the second one considers three classes (hat, cap and no hat/cap), and the last one includes the full class set with the five classes (no hat/cap, cap, small size hat, medium size hat, and large size hat). The achieved performance is satisfactory in every case: the average classification rates for the first level reaches 95.25%, for the second one is 92.34%, and for the full class set equals 84.60%. In addition, the online stage processing time is 5.75 ms per frame in a standard PC, thus allowing for real-time operation.
Highlights
People detection and human behavior analysis in video-surveillance applications are already classic research topics in computer vision, artificial intelligence, and machine learning areas but are still an open issue, with some commercial solutions performing some basic tasks with reasonable accuracy but still not available for other higher-level understanding tasks
As described in the introduction, in this work, we propose an approach for the classification of headgear accessories only using depth information provided by a ToF sensor located in an overhead position
5.75 ms per frame) of different headgear accessories, by only using the depth information provided by a ToF camera placed in an overhead position
Summary
People detection and human behavior analysis in video-surveillance applications are already classic research topics in computer vision, artificial intelligence, and machine learning areas but are still an open issue, with some commercial solutions performing some basic tasks with reasonable accuracy but still not available for other higher-level understanding tasks. Technological evolution as well as machine learning algorithmic contributions facilitate and speed up more and more reliable and robust context aware solutions, making them in order to contribute to solving this part of the problem. Identity preservation is the other open issue that should be considered in order to obtain the commercial solutions demanded by the everyday most connected and technologically informed world. Time-of-Flight (ToF) cameras, that obtain depth images from the surveilled scenarios, give high-resolution images suitable for the image analysis tasks needed by the surveillance application pursuit, while at the same time preserving the privacy of surveilled people.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
