Abstract
Depth information has been used in computer vision for a wide variety of tasks. Since active range sensors are currently available at low cost, high-quality depth maps can be used as relevant input for many applications. Background subtraction and video segmentation algorithms can be improved by fusing depth and color inputs, which are complementary and allow one to solve many classic color segmentation issues. In this paper, we describe one fusion method to combine color and depth based on an advanced color-based algorithm. This technique has been evaluated by means of a complete dataset recorded with Microsoft Kinect, which enables comparison with the original method. The proposed method outperforms the others in almost every test, showing more robustness to illumination changes, shadows, reflections and camouflage.
Highlights
In recent years, there has been an increase of interest in the application of computer vision to video surveillance tasks
We propose an adaptation of the Codebook background subtraction algorithm [8], which fuses depth and color information to segment foreground regions, focused on video analytics
Since we are focused on the use of consumer depth sensors, we have recorded and manually segmented some sequences by using Kinect [21], any kind of active sensor would have been appropriate, too (ASUS Xtion PRO [20] or ToF-cameras [19])
Summary
There has been an increase of interest in the application of computer vision to video surveillance tasks. Cristani et al [28] proposes a comprehensive review of background subtraction techniques, focusing on different sensor channels, including systems based on stereo cameras. Crabb et al [25], Zhu et al [26] and Schiller et al [27] focus on the combination of color and depth information obtained by low-resolution ToF cameras Due to this low resolution (160 × 120, 176 × 144 and 204 × 204, respectively), efforts must be made to reduce inaccuracies, specially at object boundaries. We propose an adaptation of the Codebook background subtraction algorithm [8], which fuses depth and color information to segment foreground regions, focused on video analytics.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.