Abstract
Many modern computer vision systems include several modules that perform different processing operations packaged as a single pipeline architecture. This generally introduces a challenge in the evaluation process since most datasets provide evaluation data for just one of the operations. In this paper, we present an RGB-D dataset that was designed from first principles to cater for applications that involve salient object detection, segmentation, inpainting and blending techniques. This addresses a gap in the evaluation of image inpainting and blending applications that generally rely on subjective evaluation due to the lack of availability of comparative data. A set of experiments were carried out to demonstrate how the COTS dataset can be used to evaluate these different applications. This dataset includes a variety of scenes, where each scene is captured multiple times, each time adding a new object to the previous scene. This allows for a comparative analysis at pixel level in image inpainting and blending applications. Moreover, all objects were manually labeled in order to offer the possibility of salient object detection even in scenes that contain multiple objects. An online test with 1267 participants was also carried out, and this dataset also includes the click coordinates of users' selection for every image, introducing a user interaction dimension in the same RGB-D dataset. This dataset was also validated using state of the art techniques, obtaining an $F_\beta $ of 0.957 in salient object detection and a mean (Intersection over Union) IoU of 0.942 in Segmentation. Results demonstrate that the COTS dataset introduces novel possibilities for the evaluation of computer vision applications.
Highlights
Modern computer vision applications are composed of a number of pipelined modules, each carrying out specific functions
This section focuses on RGBD datasets that center on small objects since these are solely the ones comparable to the dataset being introduced in this paper
It could be concluded that the study of saliency detection algorithms in relation to RGB-D content is seen as a current challenge for this particular area [13], [21], [23] and the dataset being proposed in this paper aims to explore this further
Summary
Modern computer vision applications are composed of a number of pipelined modules, each carrying out specific functions These include image salient object detection, segmentation, inpainting and blending. Inpainting or object removal applications are normally evaluated using a mean opinion score (MOS) methodology [2] While this approach serves its purpose and has its relevance from an image quality perspective, it lacks the objective rigour that is sometimes expected out of comparative results. This dataset allows for the evaluation of such techniques by providing an actual instance of the scene without the inpainted object.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: 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.
