Fall detection based on fused saliency maps
- PDF / 2,503,034 Bytes
- 18 Pages / 439.37 x 666.142 pts Page_size
- 55 Downloads / 261 Views
Fall detection based on fused saliency maps Hongjun Li 1,2,3,4
& Chaobo Li
1
& Yupeng Ding
5
Received: 3 June 2020 / Revised: 18 August 2020 / Accepted: 25 August 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Fall detection is drawing more attention from both academia and industry. The human body occupies smaller space relative to the background in images, so the complex background affects the extraction of human fall or non-fall features. In order to reduce the interference of the complex background, a fall detection method based on fused saliency maps is proposed, which consists of saliency maps generation model and fall detection model. For saliency maps generation model, M-level segmentation is to obtain segmented images in different level. The saliency detection mainly uses two-stream convolutional neural network extract global and local features to generate the saliency maps. The saliency maps fusion automatically learns the weights according to mean structural similarity for fusing saliency maps. For fall detection model, a simple deep network is constructed to extract the discriminant features of fall or non-fall, where the fused saliency maps is used. Experimental result show that the proposed method achieves 99.67% and 98.92% accuracy on UR Fall Detection and our selfbuilt NT Fall Detection database, respectively. And the convergence speed is fastest compared with those of using RGB images and depth images. The proposed fall detection method that can reduce the interference of complex background outperforms the other methods in terms of higher accuracy and faster convergence. Keywords Fall detection . Saliency maps . Fusion . Deep network
1 Introduction Various physiological functions of the human are deteriorating seriously with the increase of age, and accidents such as fall happened more frequently [5]. So fall detection is an important * Hongjun Li [email protected] Chaobo Li [email protected] Yupeng Ding [email protected] Extended author information available on the last page of the article
Multimedia Tools and Applications
topic in human abnormal behavior detection, especially for the elderly living alone. Statistics show that fall is the primary reason of injury for seniors aged 79 or older, and the second leading cause of injury for all age groups [22]. A survey shows that 35% people fall at least once a year among the seniors aged 65 or older [3]. The demand for surveillance systems, especially for fall detection, has increased with the development of health care industry and the rapid growth of the population of the elderly in the world [14]. Therefore, there is a great need for a real-time and accurate algorithm to detect fall event. The existing methods for fall detection that can be mainly divided into two parts: based on non-visual sensors and exclusively vision-based methods [2, 7, 12]. The methods based on non-visual sensors bring discomfort feeling to person due to wearable devices. The visionbased methods can process the in
Data Loading...
