Chunqi Gao

Chunqi Gao

Auto-generated profile, based on publicly available information

Chunqi Gao


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 November 2022 in Agriculture
Verified
Journal Article
Open access
PDF file
JYJianhao Yin
Jianhao Yin
JWJunfeng Wu
Junfeng Wu
CGChunqi Gao
Chunqi Gao
ZJZhong-ai Jiang
Zhong-ai Jiang
With the continuous development of industrial aquaculture and artificial intelligence technology, the trend of the use of automation and intelligence in aquaculture is becoming more and more obvious, and the speed of the related technical development is becoming faster and faster. Individual fish recognition could provide key technical support for fish growth monitoring, bait feeding and density estimation, and also provide strong data support for fish precision farming. However, individual fish recognition faces significant hurdles due to the underwater environment complexity, high visual similarity of individual fish and the real-time aspect of the process. In particular, the complex and changeable underwater environment makes it extremely difficult to detect individual fish and extract biological features extraction. In view of the above problems, this paper proposes an individual fish recognition method based on lightweight convolutional neural network (LIFRNet). This proposed method could extract the visual features of underwater moving fish accurately and efficiently and give each fish unique identity recognition information. The method proposed in this paper consists of three parts: the underwater fish detection module, underwater individual fish recognition module and result visualization module. In order to improve the accuracy and real-time availability of recognition, this paper proposes a lightweight backbone network for fish visual feature extraction. This research constructed a dataset for individual fish recognition (DlouFish), and the fish in dataset were manually sorted and labeled. The dataset contains 6950 picture information instances of 384 individual fish. In this research, simulation experiments were carried out on the DlouFish dataset. Compared with YOLOV4-Tiny and YOLOV4, the accuracy of the proposed method in fish detection was increased by 5.12% and 3.65%, respectively. Additionally, the accuracy of individual fish recognition reached 97.8%.

25 October 2022 in Electronics
Verified
Journal Article
Open access
PDF file
CGChunqi Gao
Chunqi Gao
JWJunfeng Wu
Junfeng Wu
HYHong Yu
Hong Yu
JYJianhao Yin
Jianhao Yin
SGShihao Guo
Shihao Guo
Fish individual recognition technology is one of the key technologies to realize automated farming. Aiming at the deficiencies in the existing animal individual recognition technology, this paper proposes a method for individual recognition of underwater fish based on deep learning technology, which is divided into two parts: fish individual object detection and fish individual recognition. In the object detection part, the research has improved a new object detection for underwater fish based on the YOLOv4 algorithm, which changed the feature extraction network in YOLOv4 from CSP Darknet53 to Mobilenetv3 and changed the 3 × 3 convolution in the enhanced feature extraction network PANet to depthwise separable convolution. Compared with the original YOLOv4, the mean average precision is improved by 1.97%. For individual recognition, an algorithm called FIRN (Fish Individual Recognition Network) for individual recognition of underwater fish is proposed. The feature extraction network of the algorithm uses the improved ResNext50, and the loss function uses Arcface Loss. The CBAM attention module is introduced in the residual block of ResNext50, the max-pooling layer in the trunk is removed, and dilated convolution is introduced in the residual block, which increases the receptive field and improves the ability of feature extraction. Experiments show that the FIEN algorithm can enhance the compactness within a class while ensuring the separability between classes, and has a better recognition effect than other algorithms.