Fast Classification and Detection of Fish Images with YOLOv2

Wang, Mengfan; Liu, Mingyong; Zhang, Feihu; Guo, Liheng; Guo, Jiaojiao; Wang, Lu

doi:10.1109/oceanskobe.2018.8559141

Cited by 23 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The architecture of this neural network is a convolutional neural network with the YOLOv2 (You Only Look Once) structure. It includes sequential convolution layers with the function ReLU (Rectified Linear Unit), layers pooling for feature map definition, and a fully connected neural network for classification [ 127 , 128 , 129 , 130 ].…”

Section: Control System Design and Robot Arm Simulationmentioning

confidence: 99%

“…To train this type of network, a set of images and an annotation in .json format is necessary, with detailed information about the location of the class object (coordinates in 2D space) and the class itself. The following parameters were chosen for the neural network using Create ML [ 128 , 129 , 130 , 136 ] ( Figure 16 ): the algorithm is the complete network (trains a complete object detection network based on YOLOv2 architecture); the number of epochs is 5000; the batch size is automatic; and the grid size is 13 × 13.…”

Section: Object Recognition In Robot Working Space Using Convolutiona...mentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Techniques for Increasing Efficiency of the Robot’s Sensor and Control Information Processing

Kondratenko

Atamanyuk

Sidenko

et al. 2022

Sensors

View full text Add to dashboard Cite

Real-time systems are widely used in industry, including technological process control systems, industrial automation systems, SCADA systems, testing, and measuring equipment, and robotics. The efficiency of executing an intelligent robot’s mission in many cases depends on the properties of the robot’s sensor and control systems in providing the trajectory planning, recognition of the manipulated objects, adaptation of the desired clamping force of the gripper, obstacle avoidance, and so on. This paper provides an analysis of the approaches and methods for real-time sensor and control information processing with the application of machine learning, as well as successful cases of machine learning application in the synthesis of a robot’s sensor and control systems. Among the robotic systems under investigation are (a) adaptive robots with slip displacement sensors and fuzzy logic implementation for sensor data processing, (b) magnetically controlled mobile robots for moving on inclined and ceiling surfaces with neuro-fuzzy observers and neuro controllers, and (c) robots that are functioning in unknown environments with the prediction of the control system state using statistical learning theory. All obtained results concern the main elements of the two-component robotic system with the mobile robot and adaptive manipulation robot on a fixed base for executing complex missions in non-stationary or uncertain conditions. The design and software implementation stage involves the creation of a structural diagram and description of the selected technologies, training a neural network for recognition and classification of geometric objects, and software implementation of control system components. The Swift programming language is used for the control system design and the CreateML framework is used for creating a neural network. Among the main results are: (a) expanding the capabilities of the intelligent control system by increasing the number of classes for recognition from three (cube, cylinder, and sphere) to five (cube, cylinder, sphere, pyramid, and cone); (b) increasing the validation accuracy (to 100%) for recognition of five different classes using CreateML (YOLOv2 architecture); (c) increasing the training accuracy (to 98.02%) and testing accuracy (to 98.0%) for recognition of five different classes using Torch library (ResNet34 architecture) in less time and number of epochs compared with Create ML (YOLOv2 architecture); (d) increasing the training accuracy (to 99.75%) and testing accuracy (to 99.2%) for recognition of five different classes using Torch library (ResNet34 architecture) and fine-tuning technology; and (e) analyzing the effect of dataset size impact on recognition accuracy with ResNet34 architecture and fine-tuning technology. The results can help to choose efficient (a) design approaches for control robotic devices, (b) machine-learning methods for performing pattern recognition and classification, and (c) computer technologies for designing control systems and simulating robotic devices.

show abstract

Section: Control System Design and Robot Arm Simulationmentioning

confidence: 99%

Section: Object Recognition In Robot Working Space Using Convolutiona...mentioning

confidence: 99%

Machine Learning Techniques for Increasing Efficiency of the Robot’s Sensor and Control Information Processing

Kondratenko

Atamanyuk

Sidenko

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…More recently, there had been different versions of YOLO-model and their applications, e.g. YOLO-v1 model [12,13,14] , YOLO-v2 model [15,16,17] , and YOLO-v3 model [18,19] et al From the point of view of network architecture, the YOLO-v1 model contained 24 convolutional layers and two fully connected layers. The YOLO-v2 model removed the fully connected layers, but added a batch normalization behind each convolutional layer and performs normalization preprocessing for each batch of data.…”

Section: The Development Of the Yolo Modelmentioning

confidence: 99%

Automatic body region localization in 3D-CT images based on the improved YOLO model

Wang

Lin

et al. 2022

MATEC Web Conf.

View full text Add to dashboard Cite

Automatic body region localization in medical three-dimensional (3D)-CT images is a critical step of computerized body-wide Automatic Anatomy Recognition (AAR) system, which can be applied for radiotherapy planning and interest slices retrieving. Currently, the complex internal structure of human body and time consuming computation are the main challenges for the localization. Therefore, this paper introduces and improves the YOLO-v3 model into the body region localization for these problems. First, seven categories of body regions in a CT volume image I are defined based on the modification version of our previous work. Second, an improved YOLO-v3 model is trained to classify each axial slice into one of the seven categories. Then, the effectiveness of the proposed method is evaluated on 3D-CT images that collected from 220 subjects. The experimental results demonstrate that the slice localizing error is less than 3 NoS (Number of slices), which is competitive to the state-of-the-art methods. Beyond this, our method is simple and computationally efficient owing to its less training time, and the average computational time for localizing a volume CT images is about 3 second, which shows potential for a further application.

show abstract

“…Reference (8) is an improved Faster R-CNN marine fish classification and recognition algorithm, which uses Resnet101 as its feature extraction network and achieves a good detection accuracy. Reference (9) uses YOLOv2 for fast classification and detection of fish images and has a good performance in detection speed. Reference (10) uses YOLOv4 for underwater fish video detection in Rodan, Honduras, and performs well in the detection of fish video streams.…”

Section: Introductionmentioning

confidence: 99%

Marine Life Detection Algorithm Based on Deep Convolutional Generative Adversarial Network and ResNeXt50 with FPN Faster R-CNN Network

Wang

Serikawa

Shen

et al. 2023

The Proceedings of the 11th IIAE International Conference on Industrial Application Engineering 2023

View full text Add to dashboard Cite

The development and utilization of marine resources has always been a focus of attention, and a prerequisite for the rational development of marine resources is the understanding of the distribution of biological resources in the ocean, so the detection of marine life has become an inevitable challenge in the development of marine resources. The acquisition of marine life images by underwater cameras is particularly difficult due to the complexity of the underwater terrain and the difficulty of underwater imaging. Therefore, the detection of marine life often faces problems of difficulties in dataset acquisition, scarcity of data in the dataset and low quality of images. To address the above problems, a marine life detection algorithm based on the combination of deep convolutional generative adversarial network and ResNeXt50 with FPN Faster R-CNN network is proposed in this paper. The algorithm uses Faster R-CNN as the basic framework for marine life detection and uses deep convolutional generative adversarial network to generate data for small dataset to effectively expand the dataset without the difficulty of underwater image acquisition. For the feature extraction network, we use ResNeXt50, which employs the idea of group convolution, as the basic network for feature extraction. Then, the network is combined with feature pyramid network to enhance the feature extraction capability. The expanded dataset fed into the ResNeXt50 with FPN Faster R-CNN target detection network for training. It can be demonstrated that the detection results of expanded dataset generated by DCGAN in ResNeXt50 with FPN Faster R-CNN network is better compared to the original dataset and the Resnet50 with FPN Faster R-CNN network.

show abstract

Fast Classification and Detection of Fish Images with YOLOv2

Cited by 23 publications

References 8 publications

Machine Learning Techniques for Increasing Efficiency of the Robot’s Sensor and Control Information Processing

Machine Learning Techniques for Increasing Efficiency of the Robot’s Sensor and Control Information Processing

Automatic body region localization in 3D-CT images based on the improved YOLO model

Marine Life Detection Algorithm Based on Deep Convolutional Generative Adversarial Network and ResNeXt50 with FPN Faster R-CNN Network

Contact Info

Product

Resources

About