MTI-YOLO: A Light-Weight and Real-Time Deep Neural Network for Insulator Detection in Complex Aerial Images

Liu, Chuanyang; Wu, Yiquan; Liu, Jingjing; Han, Jiaming

doi:10.3390/en14051426

Cited by 60 publications

(41 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We proposed a new fusion algorithm for bounding boxes that gave up the NMS solution of removing bounding boxes with low confidence and adopted the method of fusing different bounding boxes of the same object. In fact, the weight coefficients s was introduced in the fusion process, and the weight coefficients of each bounding box are calculated as shown in Equation (14).…”

Section: Fusion Methods For Bounding Boxesmentioning

confidence: 99%

See 1 more Smart Citation

GANsformer: A Detection Network for Aerial Images with High Performance Combining Convolutional Network and Transformer

Zhang

Liu

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

There has been substantial progress in small object detection in aerial images in recent years, due to the extensive applications and improved performances of convolutional neural networks (CNNs). Typically, traditional machine learning algorithms tend to prioritize inference speed over accuracy. Insufficient samples can cause problems for convolutional neural networks, such as instability, non-convergence, and overfitting. Additionally, detecting aerial images has inherent challenges, such as varying altitudes and illuminance situations, and blurred and dense objects, resulting in low detection accuracy. As a result, this paper adds a transformer backbone attention mechanism as a branch network, using the region-wide feature information. This paper also employs a generative model to expand the input aerial images ahead of the backbone. The respective advantages of the generative model and transformer network are incorporated. On the dataset presented in this study, the model achieves 96.77% precision, 98.83% recall, and 97.91% mAP by adding the Multi-GANs module to the one-stage detection network. These three indices are enhanced by 13.9%, 20.54%, and 10.27%, respectively, when compared to the other detection networks. Furthermore, this study provides an auto-pruning technique that may achieve 32.2 FPS inference speed with a minor performance loss while responding to the real-time detection task’s usage environment. This research also develops a macOS application for the proposed algorithm using Swift development technology.

show abstract

Section: Fusion Methods For Bounding Boxesmentioning

confidence: 99%

“…Fortunately, some scholars have proposed various methods to tackle the problem of small object detection in aerial images mentioned above. For example, Chuanyang Liu et al [14] developed an MTI-YOLO network for detecting insulators in complicated aerial pictures. They gathered composite insulator photos from various scenes and created a CCIN detection dataset.…”

mentioning

confidence: 99%

GANsformer: A Detection Network for Aerial Images with High Performance Combining Convolutional Network and Transformer

Zhang

Liu

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Liu et al [23] proposed an improved RetinaNet-based defect insulatordetection algorithm, which corrected the shortcomings of the Apriori-based RetinaNet anchor box extraction mechanism and used the improved K-means++ algorithm [24] to redesign the number and size of anchor boxes, construct a feature pyramid based on DenseNet as the backbone network, and the experimental results show that this method has obvious advantages in the detection accuracy of insulator defects. Liu et al [25] proposed an improved YOLO tiny (MTI-YOLO) insulator-detection algorithm, which uses a multi-scale fusion and spatial pyramid pooling (SSP) model and verified the results by comparing with YOLO tiny and YOLO v2. The average accuracy of the proposed algorithm is significantly higher than the above two algorithms, and it can achieve good performance under the condition of complex background and high exposure.…”

Section: Introductionmentioning

confidence: 99%

ARG-Mask RCNN: An Infrared Insulator Fault-Detection Network Based on Improved Mask RCNN

Zhou¹,

Wang²,

Li³

2022

Sensors

View full text Add to dashboard Cite

Traditional power equipment defect-detection relies on manual verification, which places a high demand on the verifier’s experience, as well as a high workload and low efficiency, which can lead to false detection and missed detection. The Mask of the regions with CNN features (Mask RCNN) deep learning model is used to provide a defect-detection approach based on the Mask RCNN of Attention, Rotation, Genetic algorithm (ARG-Mask RCNN), which employs infrared imaging as the data source to assess the features of damaged insulators. For the backbone network of Mask RCNN, the structure of Residual Network 101 (ResNet101) is improved and the attention mechanism is added, which makes the model more alert to small targets and can quickly identify the location of small targets, improve the loss function, integrate the rotation mechanism into the loss function formula, and generate an anchor frame where a rotation angle is used to accurately locate the fault location. The initial hyperparameters of the network are improved, and the Genetic Algorithm Combined with Gradient Descent (GA-GD) algorithm is used to optimize the model hyperparameters, so that the model training results are as close to the global best as possible. The experimental results show that the average accuracy of the insulator fault-detection method proposed in this paper is as high as 98%, and the number of frames per second (FPS) is 5.75, which provides a guarantee of the safe, stable, and reliable operation of our country’s power system.

show abstract

“…23 In order to obtain a better trade-off among accuracy, running time and memory storage, a modified YOLO-tiny network model was proposed for insulator detection in complex aerial images. 24 However, neither of the above two references involves the task of visual servoing control.…”

Section: Introductionmentioning

confidence: 99%

Robotic grasping method of bolster spring based on image-based visual servoing with YOLOv3 object detection algorithm

Liu

Tao

et al. 2021

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

In this paper, to address the problem of automatic positioning and grasping of bolster spring with complex geometric features and cluttered background, a novel image-based visual servoing (IBVS) control method based on the corner points features of YOLOv3 object detection bounding box is proposed and applied to the robotic grasping system of bolster spring. The YOLOv3 object detection model is used to detect and position the bolster spring and then based on the corner points features of the bolster spring bounding box, the IBVS controller is designed to drive the end effector of the robot to the desired pose. This method adopts the approach-align-grasp control strategy to achieve the grasping of the bolster spring, which is very robust to the calibration parameter errors of the camera and the robot model. With the help of Robotics and Machine Vision Toolboxes in Matlab, IBVS simulation analysis based on feature points is carried out. The results show that it is reasonable to use the corner points of the object detection bounding box as image features under the initial pose where the image plane is parallel to the object plane. The positioning and grasping experiments are conducted on the robotic grasping platform of bolster spring. The results show that this method is effective for automatic positioning and grasping of bolster spring with complex geometric features and cluttered background, and it has strong robustness to the change of illumination.

show abstract

MTI-YOLO: A Light-Weight and Real-Time Deep Neural Network for Insulator Detection in Complex Aerial Images

Cited by 60 publications

References 47 publications

GANsformer: A Detection Network for Aerial Images with High Performance Combining Convolutional Network and Transformer

GANsformer: A Detection Network for Aerial Images with High Performance Combining Convolutional Network and Transformer

ARG-Mask RCNN: An Infrared Insulator Fault-Detection Network Based on Improved Mask RCNN

Robotic grasping method of bolster spring based on image-based visual servoing with YOLOv3 object detection algorithm

Contact Info

Product

Resources

About