Improved YOLO Based Detection Algorithm for Floating Debris in Waterway

Various floating debris in the waterway can be used as one kind of visual index to measure the water quality. The traditional image processing method is difficult to meet the requirements of real-time monitoring of floating debris in the waterway due to the complexity of the environment, such as reflection of sunlight, obstacles of water plants, a large difference between the near and far target scale, and so on. To address these issues, an improved YOLOv5s (FMA-YOLOv5s) algorithm by adding a feature map attention (FMA) layer at the end of the backbone is proposed. The mosaic data augmentation is applied to enhance the detection effect of small targets in training. A data expansion method is introduced to expand the training dataset from 1920 to 4800, which fuses the labeled target objects extracted from the original training dataset and the background images of the clean river surface in the actual scene. The comparisons of accuracy and rapidity of six models of this algorithm are completed. The experiment proves that it meets the standards of real-time object detection.

Download Full-text

A New Real-Time Detection and Tracking Method in Videos for Small Target Traffic Signs

Applied Sciences ◽

10.3390/app11073061 ◽

2021 ◽

Vol 11 (7) ◽

pp. 3061

Author(s):

Shaojian Song ◽

Yuanchao Li ◽

Qingbao Huang ◽

Gang Li

Keyword(s):

Real Time ◽

Data Augmentation ◽

Input Image ◽

Small Sample ◽

Traffic Signs ◽

Feature Map ◽

Detection And Tracking ◽

Detailed Method ◽

Tracking Ability ◽

Small Targets

It is a challenging task for self-driving vehicles in Real-World traffic scenarios to find a trade-off between the real-time performance and the high accuracy of the detection, recognition, and tracking in videos. This issue is addressed in this paper with an improved YOLOv3 (You Only Look Once) and a multi-object tracking algorithm (Deep-Sort). First, data augmentation is employed for small sample traffic signs to address the problem of an extremely unbalanced distribution of different samples in the dataset. Second, a new architecture of YOLOv3 is proposed to make it more suitable for detecting small targets. The detailed method is (1) removing the output feature map corresponding to the 32-times subsampling of the input image in the original YOLOv3 structure to reduce its computational costs and improve its real-time performances; (2) adding an output feature map of 4-times subsampling to improve its detection capability for the small traffic signs; (3) Deep-Sort is integrated into the detection method to improve the precision and robustness of multi-object detection, and the tracking ability in videos. Finally, our method demonstrated better detection capabilities, with respect to state-of-the-art approaches, which precision, recall and mAP is 91%, 90%, and 84.76% respectively.

Download Full-text

Multidirection Object Detection in Aerial View of Traffic Target under Complex Scenes

Complexity ◽

10.1155/2021/5597168 ◽

2021 ◽

Vol 2021 ◽

pp. 1-9

Author(s):

Zeqing Zhang ◽

Weiwei Lin ◽

Yuqiang Zheng

Keyword(s):

Object Detection ◽

Expansion Method ◽

Detection Algorithm ◽

Backbone Network ◽

Unique Data ◽

Complex Scenes ◽

Aerial View ◽

Information Detection ◽

General Object ◽

Data Expansion

Focusing on DOTA, the multidirectional object dataset in aerial view of vehicles, CMDTD has been proposed. The reason why it is difficult for applying the general object detection algorithm in multidirectional object detection has been analyzed in this paper. Based on this, the detection principle of CMDTD including its backbone network and multidirectional multi-information detection end module has been studied. In addition, in view of the complexity of the scene faced by aerial view of vehicles, a unique data expansion method is proposed. At last, three datasets have been experimented using the CMDTD algorithm, proving that the cascaded multidirectional object detection algorithm with high effectiveness is superior to other methods.

Download Full-text

Audio-Based Aircraft Detection System for Safe RPAS BVLOS Operations

Electronics ◽

10.3390/electronics9122076 ◽

2020 ◽

Vol 9 (12) ◽

pp. 2076

Author(s):

Jorge Mariscal-Harana ◽

Víctor Alarcón ◽

Fidel González ◽

Juan José Calvente ◽

Francisco Javier Pérez-Grau ◽

...

Keyword(s):

Real Time ◽

Data Augmentation ◽

Detection System ◽

Cost Effective ◽

True Positive Rate ◽

Training Dataset ◽

Computational Performance ◽

Combining Data ◽

Wide Range ◽

Aircraft Detection

For the Remotely Piloted Aircraft Systems (RPAS) market to continue its current growth rate, cost-effective ‘Detect and Avoid’ systems that enable safe beyond visual line of sight (BVLOS) operations are critical. We propose an audio-based ‘Detect and Avoid’ system, composed of microphones and an embedded computer, which performs real-time inferences using a sound event detection (SED) deep learning model. Two state-of-the-art SED models, YAMNet and VGGish, are fine-tuned using our dataset of aircraft sounds and their performances are compared for a wide range of configurations. YAMNet, whose MobileNet architecture is designed for embedded applications, outperformed VGGish both in terms of aircraft detection and computational performance. YAMNet’s optimal configuration, with >70% true positive rate and precision, results from combining data augmentation and undersampling with the highest available inference frequency (i.e., 10 Hz). While our proposed ‘Detect and Avoid’ system already allows the detection of small aircraft from sound in real time, additional testing using multiple aircraft types is required. Finally, a larger training dataset, sensor fusion, or remote computations on cloud-based services could further improve system performance.

Download Full-text

Audio-Based Aircraft Detection System for Safe RPAS BVLOS Operations

10.20944/preprints202010.0343.v2 ◽

2020 ◽

Author(s):

Jorge Mariscal-Harana ◽

Víctor Alarcón ◽

Fidel González ◽

Juan José Calvente ◽

Francisco Javier Pérez-Grau ◽

...

Keyword(s):

Real Time ◽

Data Augmentation ◽

Detection System ◽

Cost Effective ◽

True Positive Rate ◽

Training Dataset ◽

Computational Performance ◽

Combining Data ◽

Wide Range ◽

Aircraft Detection

For the Remotely Piloted Aircraft Systems (RPAS) market to continue its current growth rate, cost-effective "Detect and Avoid" systems that enable safe beyond visual line of sight (BVLOS) operations are critical. We propose an audio-based "Detect and Avoid" system, composed of microphones and an embedded computer, which performs real-time inferences using a sound event detection (SED) deep learning model. Two state-of-the-art SED models, YAMNet and VGGish, are fine-tuned using our dataset of aircraft sounds and their performances are compared for a wide range of configurations. YAMNet, whose MobileNet architecture is designed for embedded applications, outperformed VGGish both in terms of aircraft detection and computational performance. YAMNet's optimal configuration, with > 70% true positive rate and precision, results from combining data augmentation and undersampling with the highest available inference frequency (i.e. 10 Hz). While our proposed "Detect and Avoid" system already allows the detection of small aircraft from sound in real time, additional testing using multiple aircraft types is required. Finally, a larger training dataset, sensor fusion, or remote computations on cloud-based services could further improve system performance.

Download Full-text

Real-Time Conveyor Belt Deviation Detection Algorithm Based on Multi-Scale Feature Fusion Network

Algorithms ◽

10.3390/a12100205 ◽

2019 ◽

Vol 12 (10) ◽

pp. 205 ◽

Cited By ~ 1

Author(s):

Chan Zeng ◽

Junfeng Zheng ◽

Jiangyun Li

Keyword(s):

Feature Extraction ◽

Real Time ◽

Load Distribution ◽

Feature Fusion ◽

Conveyor Belt ◽

Detection Algorithm ◽

Scale Feature ◽

Multi Scale ◽

High Level ◽

Detection Effect

The conveyor belt is an indispensable piece of conveying equipment for a mine whose deviation caused by roller sticky material and uneven load distribution is the most common failure during operation. In this paper, a real-time conveyor belt detection algorithm based on a multi-scale feature fusion network is proposed, which mainly includes two parts: the feature extraction module and the deviation detection module. The feature extraction module uses a multi-scale feature fusion network structure to fuse low-level features with rich position and detail information and high-level features with stronger semantic information to improve network detection performance. Depthwise separable convolutions are used to achieve real-time detection. The deviation detection module identifies and monitors the deviation fault by calculating the offset of conveyor belt. In particular, a new weighted loss function is designed to optimize the network and to improve the detection effect of the conveyor belt edge. In order to evaluate the effectiveness of the proposed method, the Canny algorithm, FCNs, UNet and Deeplab v3 networks are selected for comparison. The experimental results show that the proposed algorithm achieves 78.92% in terms of pixel accuracy (PA), and reaches 13.4 FPS (Frames per Second) with the error of less than 3.2 mm, which outperforms the other four algorithms.

Download Full-text

Traffic Sign Detection Method Based on Improved SSD

Information ◽

10.3390/info11100475 ◽

2020 ◽

Vol 11 (10) ◽

pp. 475

Author(s):

Shuai You ◽

Qiang Bi ◽

Yimu Ji ◽

Shangdong Liu ◽

Yujian Feng ◽

...

Keyword(s):

Feature Detection ◽

Detection Method ◽

Detection Algorithm ◽

Single Shot ◽

Traffic Sign ◽

Traffic Signs ◽

Adverse Weather ◽

Convolution Kernels ◽

Small Targets ◽

Detection Effect

Due to changes in illumination, adverse weather conditions, and interference from signs similar to real traffic signs, the false detection of traffic signs is possible. Nevertheless, in order to improve the detection effect of small targets, baseline SSD (single shot multibox detector) adopts a multi-scale feature detection method to improve the detection effect to some extent. The detection effect of small targets is improved, but the number of calculations needed for the baseline SSD network is large. To this end, we propose a lightweight SSD network algorithm. This method uses some 1 × 1 convolution kernels to replace some of the 3 × 3 convolution kernels in the baseline network and deletes some convolutional layers to reduce the calculation load of the baseline SSD network. Then the color detection algorithm based on the phase difference method and the connected component calculation are used to further filter the detection results, and finally, the data enhancement strategy based on the image appearance transformation is used to improve the balance of the dataset. The experimental results show that the proposed method is 3% more accurate than the baseline SSD network, and more importantly, the detection speed is also increased by 1.2 times.

Download Full-text

Animation Character Detection Algorithm Based on Clustering and Cascaded SSD

Scientific Programming ◽

10.1155/2022/4223295 ◽

2022 ◽

Vol 2022 ◽

pp. 1-10

Author(s):

Yuan Wang

Keyword(s):

Big Data ◽

Clustering Algorithm ◽

Detection Algorithm ◽

Detection Accuracy ◽

Small Target ◽

Animation Industry ◽

And Performance ◽

Small Targets ◽

High Level ◽

Detection Effect

With the evolution of the Internet and information technology, the era of big data is a new digital one. Accordingly, animation IP has been more and more widely welcomed and concerned with the continuous development of the domestic and international animation industry. Hence, animation video analysis will be a good landing application for computers. This paper proposes an algorithm based on clustering and cascaded SSD for object detection of animation characters in the big data environment. In the training process, the improved classification Loss function based on Focal Loss and Truncated Gradient was used to enhance the initial detection effect. In the detection phase, this algorithm designs a small target enhanced detection module cascaded with an SSD network. In this way, the high-level features corresponding to the small target region can be extracted separately to detect small targets, which can effectively enhance the detection effect of small targets. In order to further improve the effect of small target detection, the regional candidate box is reconstructed by a k-means clustering algorithm to improve the detection accuracy of the algorithm. Experimental results demonstrate that this method can effectively detect animation characters, and performance indicators are better than other existing algorithms.

Download Full-text

Application of Deep Learning in Integrated Pest Management: A Real-Time System for Detection and Diagnosis of Oilseed Rape Pests

Mobile Information Systems ◽

10.1155/2019/4570808 ◽

2019 ◽

Vol 2019 ◽

pp. 1-14 ◽

Cited By ~ 2

Author(s):

Yong He ◽

Hong Zeng ◽

Yangyang Fan ◽

Shuaisheng Ji ◽

Jianjian Wu

Keyword(s):

Deep Learning ◽

Integrated Pest Management ◽

Pest Management ◽

Real Time ◽

Oilseed Rape ◽

Data Augmentation ◽

Low Cost ◽

Response Speed ◽

Original Model ◽

Real Time System

In this paper, we proposed an approach to detect oilseed rape pests based on deep learning, which improves the mean average precision (mAP) to 77.14%; the result increased by 9.7% with the original model. We adopt this model to mobile platform to let every farmer able to use this program, which will diagnose pests in real time and provide suggestions on pest controlling. We designed an oilseed rape pest imaging database with 12 typical oilseed rape pests and compared the performance of five models, SSD w/Inception is chosen as the optimal model. Moreover, for the purpose of the high mAP, we have used data augmentation (DA) and added a dropout layer. The experiments are performed on the Android application we developed, and the result shows that our approach surpasses the original model obviously and is helpful for integrated pest management. This application has improved environmental adaptability, response speed, and accuracy by contrast with the past works and has the advantage of low cost and simple operation, which are suitable for the pest monitoring mission of drones and Internet of Things (IoT).

Download Full-text

GPR B-Scan Image Denoising via Multi-Scale Convolutional Autoencoder with Data Augmentation

Electronics ◽

10.3390/electronics10111269 ◽

2021 ◽

Vol 10 (11) ◽

pp. 1269

Author(s):

Jiabin Luo ◽

Wentai Lei ◽

Feifei Hou ◽

Chenghao Wang ◽

Qiang Ren ◽

...

Keyword(s):

Image Denoising ◽

Data Augmentation ◽

Noise Suppression ◽

Random Noise ◽

Similarity Index ◽

Structural Similarity ◽

Training Dataset ◽

Generative Adversarial Network ◽

Multi Scale ◽

Convolutional Autoencoder

Ground-penetrating radar (GPR), as a non-invasive instrument, has been widely used in civil engineering. In GPR B-scan images, there may exist random noise due to the influence of the environment and equipment hardware, which complicates the interpretability of the useful information. Many methods have been proposed to eliminate or suppress the random noise. However, the existing methods have an unsatisfactory denoising effect when the image is severely contaminated by random noise. This paper proposes a multi-scale convolutional autoencoder (MCAE) to denoise GPR data. At the same time, to solve the problem of training dataset insufficiency, we designed the data augmentation strategy, Wasserstein generative adversarial network (WGAN), to increase the training dataset of MCAE. Experimental results conducted on both simulated, generated, and field datasets demonstrated that the proposed scheme has promising performance for image denoising. In terms of three indexes: the peak signal-to-noise ratio (PSNR), the time cost, and the structural similarity index (SSIM), the proposed scheme can achieve better performance of random noise suppression compared with the state-of-the-art competing methods (e.g., CAE, BM3D, WNNM).

Download Full-text

Real-time 2D–3D door detection and state classification on a low-power device

SN Applied Sciences ◽

10.1007/s42452-021-04588-3 ◽

2021 ◽

Vol 3 (5) ◽

Author(s):

João Gaspar Ramôa ◽

Vasco Lopes ◽

Luís A. Alexandre ◽

S. Mogo

Keyword(s):

Low Power ◽

Real Time ◽

Object Classification ◽

Semantic Segmentation ◽

Detection Algorithm ◽

Power Device ◽

Indoor Environments ◽

State Classification ◽

Segmentation Algorithms ◽

Indoor Spaces

AbstractIn this paper, we propose three methods for door state classification with the goal to improve robot navigation in indoor spaces. These methods were also developed to be used in other areas and applications since they are not limited to door detection as other related works are. Our methods work offline, in low-powered computers as the Jetson Nano, in real-time with the ability to differentiate between open, closed and semi-open doors. We use the 3D object classification, PointNet, real-time semantic segmentation algorithms such as, FastFCN, FC-HarDNet, SegNet and BiSeNet, the object detection algorithm, DetectNet and 2D object classification networks, AlexNet and GoogleNet. We built a 3D and RGB door dataset with images from several indoor environments using a 3D Realsense camera D435. This dataset is freely available online. All methods are analysed taking into account their accuracy and the speed of the algorithm in a low powered computer. We conclude that it is possible to have a door classification algorithm running in real-time on a low-power device.

Download Full-text