Ablation studies on YOLOFruit detection algorithm for fruit harvesting robot using deep learning

Abstract Fruit detection algorithm as an integral part of harvesting robot is expected to be robust, accurate, and fast against environmental factors such as occlusion by stem and leaves, uneven illumination, overlapping fruit and many more. For this reason, this paper explored and compared ablation studies on proposed YOLOFruit, YOLOv4, and YOLOv5 detection algorithms. The final selected YOLOFruit algorithm used ResNet43 backbone with Combined activation function for feature extraction, Spatial Pyramid Pooling Network (SPPNet) for detection accuracies, Feature Pyramid Network (FPN) for feature pyramids, Distance Intersection Over Union-Non Maximum Suppression (DIoU-NMS) for detection efficiency and accuracy, and Complete Intersection Over Union (CIoU) loss for faster and better performance. The obtained results showed that the average detection accuracy of YOLOFruit at 86.2% is 1% greater than YOLOv4 at 85.2% and 4.3% higher than YOLOv5 at 81.9%, while the detection time of YOLOFruit at 11.9ms is faster than YOLOv4 at 16.6ms, but not with YOLOv5 at 2.7ms. Hence, the YOLOFruit detection algorithm is highly prospective for better generalization and real-time fruit detection.

Download Full-text

Multi-Scale Feature Pyramid Network: A Heavily Occluded Pedestrian Detection Network Based on ResNet

Sensors ◽

10.3390/s21051820 ◽

2021 ◽

Vol 21 (5) ◽

pp. 1820

Author(s):

Xiaotao Shao ◽

Qing Wang ◽

Wei Yang ◽

Yun Chen ◽

Yi Xie ◽

...

Keyword(s):

Semantic Information ◽

Detection System ◽

Pedestrian Detection ◽

Detection Accuracy ◽

The Public ◽

Scale Feature ◽

Detection Algorithms ◽

Multi Scale ◽

Art Works ◽

Feature Pyramid

The existing pedestrian detection algorithms cannot effectively extract features of heavily occluded targets which results in lower detection accuracy. To solve the heavy occlusion in crowds, we propose a multi-scale feature pyramid network based on ResNet (MFPN) to enhance the features of occluded targets and improve the detection accuracy. MFPN includes two modules, namely double feature pyramid network (FPN) integrated with ResNet (DFR) and repulsion loss of minimum (RLM). We propose the double FPN which improves the architecture to further enhance the semantic information and contours of occluded pedestrians, and provide a new way for feature extraction of occluded targets. The features extracted by our network can be more separated and clearer, especially those heavily occluded pedestrians. Repulsion loss is introduced to improve the loss function which can keep predicted boxes away from the ground truths of the unrelated targets. Experiments carried out on the public CrowdHuman dataset, we obtain 90.96% AP which yields the best performance, 5.16% AP gains compared to the FPN-ResNet50 baseline. Compared with the state-of-the-art works, the performance of the pedestrian detection system has been boosted with our method.

Download Full-text

GC-YOLOv3: You Only Look Once with Global Context Block

Electronics ◽

10.3390/electronics9081235 ◽

2020 ◽

Vol 9 (8) ◽

pp. 1235

Author(s):

Yang Yang ◽

Hongmin Deng

Keyword(s):

Object Detection ◽

Irrelevant Information ◽

Detection Algorithm ◽

Visual Object ◽

Detection Accuracy ◽

Feature Maps ◽

Average Precision ◽

Global Context ◽

Pascal Voc ◽

Feature Pyramid

In order to make the classification and regression of single-stage detectors more accurate, an object detection algorithm named Global Context You-Only-Look-Once v3 (GC-YOLOv3) is proposed based on the You-Only-Look-Once (YOLO) in this paper. Firstly, a better cascading model with learnable semantic fusion between a feature extraction network and a feature pyramid network is designed to improve detection accuracy using a global context block. Secondly, the information to be retained is screened by combining three different scaling feature maps together. Finally, a global self-attention mechanism is used to highlight the useful information of feature maps while suppressing irrelevant information. Experiments show that our GC-YOLOv3 reaches a maximum of 55.5 object detection mean Average Precision (mAP)@0.5 on Common Objects in Context (COCO) 2017 test-dev and that the mAP is 5.1% higher than that of the YOLOv3 algorithm on Pascal Visual Object Classes (PASCAL VOC) 2007 test set. Therefore, experiments indicate that the proposed GC-YOLOv3 model exhibits optimal performance on the PASCAL VOC and COCO datasets.

Download Full-text

An Efficient Robust Multiple Watermarking Algorithm for Vector Geographic Data

Information ◽

10.3390/info9120296 ◽

2018 ◽

Vol 9 (12) ◽

pp. 296 ◽

Cited By ~ 2

Author(s):

Yingying Wang ◽

Chengsong Yang ◽

Changqing Zhu ◽

Kaimeng Ding

Keyword(s):

Detection Efficiency ◽

Detection Threshold ◽

Detection Algorithm ◽

Multiple Watermarking ◽

Detection Model ◽

Detection Algorithms ◽

Geographic Data ◽

Multiple Watermarks ◽

Watermark Algorithm ◽

Made In

Vector geographic data play an important role in location information services. Digital watermarking has been widely used in protecting vector geographic data from being easily duplicated by digital forensics. Because the production and application of vector geographic data refer to many units and departments, the demand for multiple watermarking technology is increasing. However, multiple watermarking algorithm for vector geographic data draw less attention, and there are many urgent problems to be solved. Therefore, an efficient robust multiple watermark algorithm for vector geographic data is proposed in this paper. The coordinates in vector geographic data are first randomly divided into non-repetitive sets. The multiple watermarks are then embedded into the different sets. In watermark detection correlation, the Lindeberg theory is used to build a detection model and to confirm the detection threshold. Finally, experiments are made in order to demonstrate the detection algorithm, and to test its robustness against common attacks, especially against cropping attacks. The experimental results show that the proposed algorithm is robust against the deletion of vertices, addition of vertices, compression, and cropping attacks. Moreover, the proposed detection algorithm is compatible with single watermarking detection algorithms, and it has good performance in terms of detection efficiency.

Download Full-text

Small Target Detection Algorithm Based on Transfer Learning and Deep Separable Network

Journal of Sensors ◽

10.1155/2021/9006288 ◽

2021 ◽

Vol 2021 ◽

pp. 1-10

Author(s):

Peng Wang ◽

Haiyan Wang ◽

Xiaoyan Li ◽

Lingling Zhang ◽

Ruohai Di ◽

...

Keyword(s):

Transfer Learning ◽

Target Detection ◽

Activation Function ◽

Detection Algorithm ◽

Detection Accuracy ◽

Small Target ◽

Data Set ◽

Small Target Detection ◽

Low Level ◽

Half Axis

With the development of deep learning, target detection from vision sensor has achieved high accuracy and efficiency. However, small target detection remains a challenge due to inadequate use of semantic information and detailed texture information of underlying features. To solve the above problems, this paper proposes a small target detection algorithm based on Mask R-CNN model which integrates transfer learning and deep separable network. Firstly, the feature pyramid fusion structure is introduced to enhance the learning effect of low-level and high-level features, especially to strengthen the information channel of low-level feature and meanwhile optimize the feature information of small target. Secondly, the ELU function is used as the activation function to solve the problem that the original activation function disappears in the negative half axis gradient. Finally, a new loss function F-Softmax combined with Focal Loss was adopted to solve the imbalance of positive and negative sample proportions. In this paper, self-made data set is used to carry out experiments, and the experimental results show that the proposed algorithm makes the detection accuracy of small targets reach 66.5%.

Download Full-text

TWO-LEAD JOINT DETECTION ALGORITHM OF QRS COMPLEXES IN ECG SIGNAL

Journal of Mechanics in Medicine and Biology ◽

10.1142/s0219519421400728 ◽

2021 ◽

Author(s):

WANSONG XU ◽

TIANWU CHEN ◽

FANYU DU

Keyword(s):

Detection Algorithm ◽

Detection Accuracy ◽

Ecg Signal ◽

Joint Detection ◽

Ecg Signals ◽

Detection Algorithms ◽

Threshold Adjustment ◽

Current Algorithm ◽

Electrocardiogram Ecg

Objective: The detection of QRS complexes is an important part of computer-aided analysis of electrocardiogram (ECG). However, most of the existing detection algorithms are mainly for single-lead ECG signals, which requires high quality of signal. If the signal quality decreases suddenly due to some interference, then the current algorithm is easy to cause misjudgment or missed detection. To improve the detection ability of QRS complexes under sudden interference, we study the QRS complexes information on multiple leads in-depth, and propose a two-lead joint detection algorithm of QRS complexes. Methods: Firstly, the suspected QRS complexes are screened on the main lead. For the suspected QRS complexes with low confidence and the complexes that may be missed, further accurate detection and joint judgment shall be carried out at the corresponding position of the auxiliary lead. At the same time, the adaptive threshold adjustment algorithm and backtracking mechanism are used to modify the detection results. Results: The proposed detection algorithm is validated using 48 ECG records of the MIT-BIH arrhythmia database, and achieves average detection accuracy of 99.71%, sensitivity of 99.88% and positive predictivity of 99.81%. Conclusion: The proposed algorithm has high accuracy, which can effectively deal with the sudden interference of ECG signal. Meanwhile, the algorithm requires small amount of computation, and can be embedded into hardware for real-time detection.

Download Full-text

Accurate and Lightweight RailNet for Real-Time Rail Line Detection

Electronics ◽

10.3390/electronics10162038 ◽

2021 ◽

Vol 10 (16) ◽

pp. 2038

Author(s):

Zhen Tao ◽

Shiwei Ren ◽

Yueting Shi ◽

Xiaohua Wang ◽

Weijiang Wang

Keyword(s):

Real Time ◽

Detection Algorithm ◽

Social Progress ◽

Line Detection ◽

Detection Accuracy ◽

Railway Transportation ◽

Deep Convolutional Neural Networks ◽

Detection Algorithms ◽

Rail Line ◽

Binary Segmentation

Railway transportation has always occupied an important position in daily life and social progress. In recent years, computer vision has made promising breakthroughs in intelligent transportation, providing new ideas for detecting rail lines. Yet the majority of rail line detection algorithms use traditional image processing to extract features, and their detection accuracy and instantaneity remain to be improved. This paper goes beyond the aforementioned limitations and proposes a rail line detection algorithm based on deep learning. First, an accurate and lightweight RailNet is designed, which takes full advantage of the powerful advanced semantic information extraction capabilities of deep convolutional neural networks to obtain high-level features of rail lines. The Segmentation Soul (SS) module is creatively added to the RailNet structure, which improves segmentation performance without any additional inference time. The Depth Wise Convolution (DWconv) is introduced in the RailNet to reduce the number of network parameters and eventually ensure real-time detection. Afterward, according to the binary segmentation maps of RailNet output, we propose the rail line fitting algorithm based on sliding window detection and apply the inverse perspective transformation. Thus the polynomial functions and curvature of the rail lines are calculated, and rail lines are identified in the original images. Furthermore, we collect a real-world rail lines dataset, named RAWRail. The proposed algorithm has been fully validated on the RAWRail dataset, running at 74 FPS, and the accuracy reaches 98.6%, which is superior to the current rail line detection algorithms and shows powerful potential in real applications.

Download Full-text

Soft Fault Detection Algorithms for Multi-Parallel Data Streams Under the Cloud Computing

Journal of Advanced Computational Intelligence and Intelligent Informatics ◽

10.20965/jaciii.2018.p1114 ◽

2018 ◽

Vol 22 (7) ◽

pp. 1114-1119

Author(s):

Hongbing Meng ◽

Keyword(s):

Fault Detection ◽

Data Streams ◽

Data Stream ◽

Error Probability ◽

Detection Efficiency ◽

Detection Algorithm ◽

Traditional Methods ◽

Detection Algorithms ◽

Parallel Data ◽

Soft Fault

In the fault detection of multi-parallel data streams, the error probability of traditional methods is large, which cannot effectively meet the soft fault detection for multi-parallel data stream, causing the problem of low detection efficiency. A soft fault detection algorithm based on adaptive multi-parallel data stream is proposed. The soft fault feature in the data stream is extracted, and the adaptive soft fault detection algorithm is used to detect the fault of the multi-parallel data stream, which can overcome the disadvantages of traditional methods, effectively improve the efficiency, safety and the accuracy. Experimental results showed that the proposed method can effectively improve the efficiency of fault detection.

Download Full-text

DESIGN AND APPLICATION OF BOUNDING VOLUME HIERARCHY COLLISION DETECTION ALGORITHM BASED ON VIRTUAL SPHERE

Journal of Mechanics in Medicine and Biology ◽

10.1142/s021951941940044x ◽

2019 ◽

Vol 19 (07) ◽

pp. 1940044

Author(s):

MONAN WANG ◽

SHAOYONG CHEN ◽

QIYOU YANG

Keyword(s):

Collision Detection ◽

Detection Efficiency ◽

Vastus Lateralis ◽

Detection Algorithm ◽

Virtual Surgery ◽

Vastus Lateralis Muscle ◽

Detection Algorithms ◽

Bounding Volume ◽

High Detection Efficiency ◽

Bounding Volume Hierarchy

The result of collision detection is closely related to the further deformation or cutting action of soft tissue. In order to further improve the efficiency and stability of collision detection, in this paper, a collision detection algorithm of bounding volume hierarchy based on virtual sphere was proposed. The proposed algorithm was validated and the results show that the detection efficiency of the bounding volume hierarchy algorithm based on virtual sphere is higher than that of the serial hybrid bounding volume hierarchy algorithm and the parallel hybrid bounding volume hierarchy algorithm. Different collision detection algorithms were tested and the results show that the collision detection algorithm based on virtual sphere has high detection efficiency and good stability. As the number of triangular patches increased, the advantage was more and more obvious. Finally, the proposed algorithm was applied to two large and medium-sized virtual scenes to implement the collision detection between the vastus lateralis muscle, thigh and surgical instrument. Based on the virtual sphere, the collision detection algorithm of bounding volume hierarchy can implement efficient and stable collision detection in a virtual surgery system. Meanwhile, the algorithm can be combined with other acceleration algorithms (such as the multithread acceleration algorithm) to further improve detection efficiency.

Download Full-text

A Target Detection Algorithm for Remote Sensing Images Based on Deep Learning

Contrast Media & Molecular Imaging ◽

10.1155/2021/3474921 ◽

2021 ◽

Vol 2021 ◽

pp. 1-6

Author(s):

Yi Lv ◽

Zhengbo Yin ◽

Zhezhou Yu

Keyword(s):

Remote Sensing ◽

Deep Learning ◽

Target Detection ◽

Detection Efficiency ◽

False Positive Rate ◽

Remote Sensing Image ◽

Detection Algorithm ◽

Detection Accuracy ◽

Data Set ◽

Detection Effect

In order to improve the accuracy of remote sensing image target detection, this paper proposes a remote sensing image target detection algorithm DFS based on deep learning. Firstly, dimension clustering module, loss function, and sliding window segmentation detection are designed. The data set used in the experiment comes from GoogleEarth, and there are 6 types of objects: airplanes, boats, warehouses, large ships, bridges, and ports. Training set, verification set, and test set contain 73490 images, 22722 images, and 2138 images, respectively. It is assumed that the number of detected positive samples and negative samples is A and B, respectively, and the number of undetected positive samples and negative samples is C and D, respectively. The experimental results show that the precision-recall curve of DFS for six types of targets shows that DFS has the best detection effect for bridges and the worst detection effect for boats. The main reason is that the size of the bridge is relatively large, and it is clearly distinguished from the background in the image, so the detection difficulty is low. However, the target of the boat is very small, and it is easy to be mixed with the background, so it is difficult to detect. The MAP of DFS is improved by 12.82%, the detection accuracy is improved by 13%, and the recall rate is slightly decreased by 1% compared with YOLOv2. According to the number of detection targets, the number of false positives (FPs) of DFS is much less than that of YOLOv2. The false positive rate is greatly reduced. In addition, the average IOU of DFS is 11.84% higher than that of YOLOv2. For small target detection efficiency and large remote sensing image detection, the DFS algorithm has obvious advantages.

Download Full-text

Research on insulator defect detection algorithm of transmission line based on CenterNet

PLoS ONE ◽

10.1371/journal.pone.0255135 ◽

2021 ◽

Vol 16 (7) ◽

pp. e0255135

Author(s):

Chunming Wu ◽

Xin Ma ◽

Xiangxu Kong ◽

Haichao Zhu

Keyword(s):

Transmission Line ◽

Defect Detection ◽

Detection Method ◽

Detection Efficiency ◽

Super Resolution ◽

Reconstruction Algorithm ◽

Detection Algorithm ◽

Electric Power System ◽

Stable Operation ◽

Detection Accuracy

The reliability of the insulator has directly affected the stable operation of electric power system. The detection of defective insulators has always been an important issue in smart grid systems. However, the traditional transmission line detection method has low accuracy and poor real-time performance. We present an insulator defect detection method based on CenterNet. In order to improve detection efficiency, we simplified the backbone network. In addition, an attention mechanism is utilized to suppress useless information and improve the accuracy of network detection. In image preprocessing, the blurring of some detected images results in the samples being discarded, so we use super-resolution reconstruction algorithm to reconstruct the blurred images to enhance the dataset. The results show that the AP of the proposed method reaches 96.16% and the reasoning speed reaches 30FPS under the test condition of NVIDIA GTX 1080 test conditions. Compared with Faster R-CNN, YOLOV3, RetinaNet and FSAF, the detection accuracy of proposed method is greatly improved, which fully proves the effectiveness of the proposed method.

Download Full-text