RGB-D Indiscernible Object Counting in Underwater Scenes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Guolei, Cheng, Xiaogang, An, Zhaochong, Wang, Xiaokang, Liu, Yun, Fan, Deng-Ping, Cheng, Ming-Ming, Van Gool, Luc
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917890224029696
author Sun, Guolei
Cheng, Xiaogang
An, Zhaochong
Wang, Xiaokang
Liu, Yun
Fan, Deng-Ping
Cheng, Ming-Ming
Van Gool, Luc
author_facet Sun, Guolei
Cheng, Xiaogang
An, Zhaochong
Wang, Xiaokang
Liu, Yun
Fan, Deng-Ping
Cheng, Ming-Ming
Van Gool, Luc
contents Recently, indiscernible/camouflaged scene understanding has attracted lots of research attention in the vision community. We further advance the frontier of this field by systematically studying a new challenge named indiscernible object counting (IOC), the goal of which is to count objects that are blended with respect to their surroundings. Due to a lack of appropriate IOC datasets, we present a large-scale dataset IOCfish5K which contains a total of 5,637 high-resolution images and 659,024 annotated center points. Our dataset consists of a large number of indiscernible objects (mainly fish) in underwater scenes, making the annotation process all the more challenging. IOCfish5K is superior to existing datasets with indiscernible scenes because of its larger scale, higher image resolutions, more annotations, and denser scenes. All these aspects make it the most challenging dataset for IOC so far, supporting progress in this area. Benefiting from the recent advancements of depth estimation foundation models, we construct high-quality depth maps for IOCfish5K by generating pseudo labels using the Depth Anything V2 model. The RGB-D version of IOCfish5K is named IOCfish5K-D. For benchmarking purposes on IOCfish5K, we select 14 mainstream methods for object counting and carefully evaluate them. For multimodal IOCfish5K-D, we evaluate other 4 popular multimodal counting methods. Furthermore, we propose IOCFormer, a new strong baseline that combines density and regression branches in a unified framework and can effectively tackle object counting under concealed scenes. We also propose IOCFormer-D to enable the effective usage of depth modality in helping detect and count objects hidden in their environments. Experiments show that IOCFormer and IOCFormer-D achieve state-of-the-art scores on IOCfish5K and IOCfish5K-D, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2304_11677
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle RGB-D Indiscernible Object Counting in Underwater Scenes
Sun, Guolei
Cheng, Xiaogang
An, Zhaochong
Wang, Xiaokang
Liu, Yun
Fan, Deng-Ping
Cheng, Ming-Ming
Van Gool, Luc
Computer Vision and Pattern Recognition
Recently, indiscernible/camouflaged scene understanding has attracted lots of research attention in the vision community. We further advance the frontier of this field by systematically studying a new challenge named indiscernible object counting (IOC), the goal of which is to count objects that are blended with respect to their surroundings. Due to a lack of appropriate IOC datasets, we present a large-scale dataset IOCfish5K which contains a total of 5,637 high-resolution images and 659,024 annotated center points. Our dataset consists of a large number of indiscernible objects (mainly fish) in underwater scenes, making the annotation process all the more challenging. IOCfish5K is superior to existing datasets with indiscernible scenes because of its larger scale, higher image resolutions, more annotations, and denser scenes. All these aspects make it the most challenging dataset for IOC so far, supporting progress in this area. Benefiting from the recent advancements of depth estimation foundation models, we construct high-quality depth maps for IOCfish5K by generating pseudo labels using the Depth Anything V2 model. The RGB-D version of IOCfish5K is named IOCfish5K-D. For benchmarking purposes on IOCfish5K, we select 14 mainstream methods for object counting and carefully evaluate them. For multimodal IOCfish5K-D, we evaluate other 4 popular multimodal counting methods. Furthermore, we propose IOCFormer, a new strong baseline that combines density and regression branches in a unified framework and can effectively tackle object counting under concealed scenes. We also propose IOCFormer-D to enable the effective usage of depth modality in helping detect and count objects hidden in their environments. Experiments show that IOCFormer and IOCFormer-D achieve state-of-the-art scores on IOCfish5K and IOCfish5K-D, respectively.
title RGB-D Indiscernible Object Counting in Underwater Scenes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2304.11677