Research
| Title： | MoFiM: A morphable fish modeling method for underwater binocular vision system |
|---|---|
| First author： | Yin, Jingfang; Zhu, Dengming; Shi, Min; Li, Zhaoxin; Duan, Ming; Mi, Xiangyuan; Wang, Zhaoqi |
| Journal： | COMPUTER ANIMATION AND VIRTUAL WORLDS |
| Years： | 2022 |
| DOI： | 10.1002/cav.2104 |
| Abstract： | Fish morphology is an essential basis for fishery management, as it can reflect the growth status of fishes. Noncontact 3D reconstruction of underwater fish is a new way to obtain fish morphology. While it is difficult to reconstruct fish on account of the inadequate information caused by fish swimming and poor underwater imaging. This article introduces a morphable fish modeling method for the underwater binocular vision system. First, we define a fish representation based on selected landmarks. Then, we propose a chirality-supervision incorporated hourglass network to estimate fish orientation and fish 2D landmarks simultaneously, and calculate fish 3D landmarks by triangulation. Next, we propose a fish modeling method which is based on 3D landmarks and introduce the optimization procedure of fish modeling. Finally, we obtain the complete 3D fish model corresponding to the input images. To train our network and build a parametric model, we constructed an underwater vision dataset and fish instance dataset respectively. We conducted experiments with grass carp as an example, and the experimental results show that our method can achieve effective fish modeling and is useful for noncontact measurement of underwater fish. |
