Learning-based Object Detection Research Articles

ODRP: a new approach for spatial street sign detection from EXIF using deep learning-based object detection, distance estimation, rotation and projection system

ODRP: a new approach for spatial street sign detection from EXIF using deep learning-based object detection, distance estimation, rotation and projection system

An Adaptive Adversarial Patch-Generating Algorithm for Defending against the Intelligent Low, Slow, and Small Target

The “low, slow, and small” target (LSST) poses a significant threat to the military ground unit. It is hard to defend against due to its invisibility to numerous detecting devices. With the onboard deep learning-based object detection methods, the intelligent LSST (ILSST) can find and detect the ground unit autonomously in a denied environment. This paper proposes an adversarial patch-based defending method to blind the ILSST by attacking its onboard object detection network. First, an adversarial influence score was established to indicate the influence of the adversarial noise on the objects. Then, based on this score, we used the least squares algorithm and Bisectional search methods to search the patch’s optimal coordinates and size. Using the optimal coordinates and size, an adaptive patch-generating network was constructed to automatically generate patches on ground units and hide the ground units from the deep learning-based object detection network. To evaluate the efficiency of our algorithm, a new LSST view dataset was collected, and extensive attacking experiments are carried out on this dataset. The results demonstrate that our algorithm can effectively attack the object detection networks, is better than state-of-the-art adversarial patch-generating algorithms in hiding the ground units from the object detection networks, and has high transferability among the object detection networks.

Multiple face mask wearer detection based on YOLOv3 approach

<div align="left"><a name="_Hlk108683337"></a><span lang="EN-US">The coronavirus disease 2019 (COVID-19) is a highly infectious disease caused by the SARS-CoV-2 coronavirus. In breaking the transmission chain of SARS-CoV-2, the government has made it compulsory for the people to wear a mask in public places to prevent COVID-19 transmission. Hence, an automated face mask detection is crucial to facilitate the monitoring process in ensuring people to wear a face mask in public. This project aims to develop an automated face and face mask detection for multiple people by applying deep learning-based object detection algorithm you only look once version 3 (YOLOv3). YOLOv3 object detection algorithm was concatenated with different backbones including ResNet-50 and Darknet-53 to develop the face and face mask detection model. Datasets were collected from online resources including Kaggle and Github and the images were filtered and labelled accordingly. The models were trained on 4393 images and evaluated based on precision, recall, mean average precision and the detection time. In conclusion, DarkNet53_YOLOv3 was chosen as the better model compared to ResNet50_YOLOv3 model with its good performance on accuracy with a mAP of 95.94% and a fast detection speed with a detection time of 50 seconds on 776 images. </span></div>

Sea-Surface Object Detection Based on Electro-Optical Sensors: A Review

Sea-surface object detection is critical for navigation safety of autonomous ships. Electro-optical (EO) sensors, such as video cameras, complement radar on board in detecting small obstacle sea-surface objects. Traditionally, researchers have used horizon detection, background subtraction, and foreground segmentation techniques to detect sea-surface objects. Recently, deep learning-based object detection technologies have been gradually applied to sea-surface object detection. This article demonstrates a comprehensive overview of sea-surface object-detection approaches where the advantages and drawbacks of each technique are compared, covering four essential aspects: EO sensors and image types, traditional object-detection methods, deep learning methods, and maritime datasets collection. In particular, sea-surface object detections based on deep learning methods are thoroughly analyzed and compared with highly influential public datasets introduced as benchmarks to verify the effectiveness of these approaches. The article also proposes the direction of future research for sea-surface object detection based on EO sensors.

Vehicle Number Plate Recognition Using Raspberry Pi

Vehicle number plate recognition (VNPR) systems have gained significant attention due to their wide range of applications in traffic management, parking enforcement, and security systems. This abstract presents an overview of a VNPR system that utilizes computer vision techniques and machine learning algorithms for license plate detection and recognition. The system is implemented using a Raspberry Pi platform, which provides a cost-effective and portable solution. The system follows a systematic approach to perform license plate recognition. Firstly, the camera captures images or video frames, which are then processed using the OpenCV library to enhance the visibility and quality of the license plates. License plate detection algorithms, employing edge detection or machine learning-based object detection techniques, are applied to locate and extract the license plate regions in the processed images. Following license plate detection, character segmentation techniques are utilized to isolate individual characters on the plate. Finally, integrated into the system, the Tesseract OCR engine recognizes the segmented characters and extracts the text information, effectively providing the license plate data.

A lightweight object detection network in low-light conditions based on depthwise separable pyramid network and attention mechanism on embedded platforms

Deep learning-based object detection algorithms have been widely used and are effective in autonomous driving. But their performance degrades dramatically under low-light conditions. The existing mitigation approach for low-light object detection uses image enhancement preprocessing to improve detection performance with limited success. In addition, this preprocessing approach incurs extra computation costs, consumes more resources, and makes it more challenging to implement the algorithm on embedded platforms. This paper proposes a novel object detection network in low-light conditions for embedded platforms. The new system consists of two innovative modules, including a lightweight low-light enhancement network DS-PyLENet and an anchor-free lightweight object detector CFEDet. DS-PyLENet is a three-level pyramid network configured with depthwise separable convolution residual blocks (DSCRBs) and multiscale DSCRBs. The CFEDet is configured with an improved EfficientNet backbone network with Coordinate Attention (CA) and vanilla MBconv, i.e., CA-fused EfficientNet, an improved Path Aggregation Network (PAN) fusion module, and an anchor-free Global Focal Loss (GFL) detection head. Two evaluation metrics, relative recall ratios, are proposed to depict the effectiveness of image enhancement on object detection more intuitively. The new model is demonstrated to be superior to the assembled model of EnlightenGAN and YOLOv5n in terms of detection accuracy and speed on GPU and embedded platforms. The testing results of the new model reveal that 83.5% mAP is achieved on the Exdark dataset and 67.4% mAP on the DarkFace dataset. The running rates of GTX 1080Ti and NVIDIA Jetson Xavier NX are 22 FPS and 2.6 FPS, respectively. The recall of CFEDet with DS-PyLENet increased to 22.1% and significantly improved over 18% with Zero-DCE and 17.2% with EnlightenGAN.

Adversarial pan-sharpening attacks for object detection in remote sensing

Pan-sharpening, as one of the most commonly used techniques in remote sensing systems, aims to fuse texture-rich PAN images and multi-spectral MS images to obtain texture-rich MS images. With the development of deep learning, CNN based Pan-sharpening methods have received more and more attention in recent years. Since Pan-sharpening technique can integrate the complementary information of Pan and MS images, researchers usually apply object detectors on these pan-sharpened images to achieve reliable detection results. However, recent studies have shown that Deep Learning-based object detection methods are vulnerable to adversarial examples, i.e., adding imperceptible noise to clean images can fool well-trained deep neural networks. It is interesting to combine the pan-sharpening technique with adversarial examples to attack object detectors in remote sensing. In this paper, we propose a framework to generate adversarial pan-sharpened images. Specifically, we propose a two-stream network to generate the pan-sharpened images, and then utilize the shape loss and label loss to perform the attack task. To guarantee the quality of pan-sharpened images, a perceptual loss is utilized to balance spectral preservation and attacking performance. Experimental results demonstrate that the proposed method can generate effective adversarial pan-sharpened images that maintain a high success rate for white-box attacks and achieve transferability for black-box attacks.

Surface defect detection method for electronic panels based on double branching and decoupling head structure.

During the production of electronic panels, surface defects will inevitably appear. How to quickly and accurately detect these defects is very important to improve product quality. However, some problems such as high cost and low accuracy are still prominent when existing manual detection and traditional techniques are used to solve such problems. Therefore, more and more computer vision techniques are proposed to solve such problems, but the current application of deep learning-based object detection networks for surface defect detection of electronic panels is in a gap. The analysis found that there are two main reasons for this phenomenon. On the one hand, the surface defects of electronic panels have their unique characteristics such as multi-scale and irregular shape, and the current object detection networks cannot effectively solve these problems. On the other hand, the regression and classification tasks coupled in the current computational mechanism of each network are commonly found to cause the problem of conflict between them, which makes it more difficult to adapt these network models to the detection tasks in this scenario. Based on this, we design a supervised object detection network for electronic panel surface defect detection scenario for the first time. The computational mechanism of this network includes a prediction box generation strategy based on the double branch structure and a detection head design strategy that decouples the regression task from the classification task. In addition, we validated the designed network and the proposed method on our own collected dataset of surface defects in electronic panels. The final results of the comparative and ablation experiments show that our proposed method achieves an average accuracy of 78.897% for 64 surface defect categories, proving that its application to electronic panel surface defect detection scenarios can achieve better results.

Detection of sperm cells by single-stage and two-stage deep object detectors

Today, infertility is a common health concern that affects approximately 15%–20% of the world population. The evaluation of male patients with infertility includes diverse examination and laboratory tests in comparison to female patients. In the evaluation of male infertility, sperm specimens are examined in terms of morphometry, concentration, and motility. Detection of sperm is the critical step to determine the concentration and motility parameters. In this study, a fusion approach of deep learning-based object detection techniques is utilized in the sperm detection problem for obtaining more accurate and consistent concentration and motility characteristics of sperm specimens. First, 12 sperm specimen videos acquired from different infertile patients were recorded. Then, regions in the video frames were labeled as sperm and non-sperm by the experts. Two different scenarios have been tested over the labeled dataset. Differently arranged train and test data ratios were also utilized for each scenario. In the first scenario, deep learning-based object detection algorithms were individually performed for the sperm detection of patient-oriented videos in terms of different train/test split ratios. Videos with the lowest mAP (mean Average Precision) values resulted in the first scenario were selected for the second scenario as target videos. The rest of the videos were used for model training without any patient-oriented manner. In the second scenario, the detection performance for more challenging videos is aimed to increase by using different videos instead of using the small part of the same video in the model training. Additionally, a fusion idea of the utilized deep learning-based techniques was proposed and performed over these low mAP resulted videos to increase the detection performance. The results are compared regarding the general mAP, class-wise APs, and training time. In the first scenario, YOLOv5 achieved the best results, while the proposed fusion approach achieved the best mAP scores in the second scenario.

Deep Learning-Based Real-Time Traffic Sign Recognition System for Urban Environments

A traffic sign recognition system is crucial for safely operating an autonomous driving car and efficiently managing road facilities. Recent studies on traffic sign recognition tasks show significant advances in terms of accuracy on several benchmarks. However, they lack performance evaluation in driving cars in diverse road environments. In this study, we develop a traffic sign recognition framework for a vehicle to evaluate and compare deep learning-based object detection and tracking models for practical validation. We collect a large-scale highway image set using a camera-installed vehicle for training models, and evaluate the model inference during a test drive in terms of accuracy and processing time. In addition, we propose a novel categorization method for urban road scenes with possible scenarios. The experimental results show that the YOLOv5 detector and strongSORT tracking model result in better performance than other models in terms of accuracy and processing time. Furthermore, we provide an extensive discussion on possible obstacles in traffic sign recognition tasks to facilitate future research through numerous experiments for each road condition.

Big Data Management Algorithms, Deep Learning-Based Object Detection Technologies, and Geospatial Simulation and Sensor Fusion Tools in the Internet of Robotic Things

The objective of this systematic review was to analyze the recently published literature on the Internet of Robotic Things (IoRT) and integrate the insights it articulates on big data management algorithms, deep learning-based object detection technologies, and geospatial simulation and sensor fusion tools. The research problems were whether computer vision techniques, geospatial data mining, simulation-based digital twins, and real-time monitoring technology optimize remote sensing robots. Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) guidelines were leveraged by a Shiny app to obtain the flow diagram comprising evidence-based collected and managed data (the search results and screening procedures). Throughout January and July 2022, a quantitative literature review of ProQuest, Scopus, and the Web of Science databases was performed, with search terms comprising “Internet of Robotic Things” + “big data management algorithms”, “deep learning-based object detection technologies”, and “geospatial simulation and sensor fusion tools”. As the analyzed research was published between 2017 and 2022, only 379 sources fulfilled the eligibility standards. A total of 105, chiefly empirical, sources have been selected after removing full-text papers that were out of scope, did not have sufficient details, or had limited rigor For screening and quality evaluation so as to attain sound outcomes and correlations, we deployed AMSTAR (Assessing the Methodological Quality of Systematic Reviews), AXIS (Appraisal tool for Cross-Sectional Studies), MMAT (Mixed Methods Appraisal Tool), and ROBIS (to assess bias risk in systematic reviews). Dimensions was leveraged as regards initial bibliometric mapping (data visualization) and VOSviewer was harnessed in terms of layout algorithms.

Non-destructive robotic sorting of cracked pistachio using deep learning

Pistachio, an agricultural product, is considered one of the guilt-free snacks due to its nutritional content, taste, and its health benefits. Usually, when it is consumed as a snack, in-shell pistachios are more desirable, whereas pistachios without their shell are ordinarily used for food preparation. One parameter important for pistachios sold as a snack is whether their shell is open. In pistachio processing plants, closed-shelled pistachios are separated with manual labor. There also exists an automated method called pin-picker machines, but as these machines harm pistachio kernels, they are undesirable. This paper offers a method to separate open-shelled pistachios from closed-shelled pistachios in an unharmful method. This method is done by using a deep learning-based object detection algorithm. In order to sort pistachios physically, a gripper and a conveyor system equipped Cartesian manipulator has been developed. In addition, a double-camera configuration is used. The key function of a double-camera configuration is to see the one-sided split on pistachios, which is hard to achieve with a single-camera configuration. Firstly, the object detection algorithm detects pistachios and gives their position with bounding boxes. Then their real-world coordinates are calculated, pistachios in both images taken with the cameras are paired, and the Cartesian manipulator separates pistachios. The detection accuracy was found as 98 % and 85 % for open-shelled pistachio and closed-shelled pistachio, respectively. With this method, closed-shelled pistachios can be sent to a cracking machine, or they can be sent to be stored for later use as they can withstand environmental effects better than open-shelled pistachios.

An improved method MSS-YOLOv5 for object detection with balancing speed-accuracy

For deep learning-based object detection, we present a superior network named MSS-YOLOv5, which not only considers the reliability in complex scenes but also promotes its timeliness to better adapt to practical scenarios. First of all, multi-scale information is integrated into different feature dimensions to improve the distinction and robustness of features. The design of the detectors increases the variety of detection boxes to accommodate a wider range of detected objects. Secondly, the pooling method is upgraded to obtain more detailed information. At last, we add the Angle cost and assign new weights to different loss functions to accelerate the convergence and improve the accuracy of network detection. In our network, we explore four variants MSS-YOLOv5s, MSS-YOLOv5m, MSS-YOLOv5x, and MSS-YOLOv5l. Experimental results of MSS-Yolov5s show that our technique improves mAP on the PASCAL VOC2007 and PASCAL 2012 datasets by 2.4% and 2.9%, respectively. Meanwhile, it maintains a fast inference speed. At the same time, the other three models have different degrees of performance improvement in terms of balancing speed and precision in challenging detection regions.

Computer Vision on X-Ray Data in Industrial Production and Security Applications: A Comprehensive Survey

X-ray imaging technology has been used for decades in clinical tasks to reveal the internal condition of different organs, and in recent years, it has become more common in other areas such as industry, security, and geography. The recent development of computer vision and machine learning techniques has also made it easier to automatically process X-ray images and several machine learning-based object (anomaly) detection, classification, and segmentation methods have been recently employed in X-ray image analysis. Due to the high potential of deep learning in related image processing applications, it has been used in most of the studies. This survey reviews the recent research on using computer vision and machine learning for X-ray analysis in industrial production and security applications and covers the applications, techniques, evaluation metrics, datasets, and performance comparison of those techniques on publicly available datasets. We also highlight some drawbacks in the published research and give recommendations for future research in computer vision-based X-ray analysis.

An Efficient Few-Shot Object Detection Method for Railway Intrusion via Fine-Tune Approach and Contrastive Learning

Railway intrusion detection plays an important role in the railway intelligent transportation system, assisting the safe operation of trains. The existing deep learning-based object detection methods excessively rely on a large number of supervision samples, and build up such a railway intrusion dataset is usually costly. The emerging few-shot object detection (FSOD) can realize object detection task by learning a small number of samples, which is a suitable candidate for railway intrusion detection. However, small databases lead to poor classification performances, and most existing FSOD methods have the drawbacks of high computational complexity and slow adaptation speed. To deal with these issues, an efficient few-shot object detection method for railway intrusion (FSRD) is proposed in this paper, extending FSOD to railway intrusion detection with few training samples to achieve good performance. A simple yet effective fine-tuning method is also developed to improve overall performance. There is a classifier head initializer to perform an appropriate initialization of the model weights and speed up the adaptation of the detector. The contrastive learning method is further introduced to cope with the misclassification. The proposed novel method is tested on a real railway intrusion dataset. Experimental results show that it achieves an average detection accuracy of 80.51 mAP50 under the setting of 30 shots. Compared with the state-of-the-art (SOTA) FSOD methods, it is capable of yielding the optimal and suboptimal performance in all settings. Furthermore, conducting extensive experiments demonstrates its good detection accuracy, fast adaptability, and satisfactory generalization ability in railway intrusion detection.

Surface Defect Detection with Limited Training Data: A Case Study on Crown Wheel Surface Inspection

This paper presents an approach to automatic surface defect detection by a deep learning-based object detection method, particularly in challenging scenarios where defects are rare, i.e., with limited training data. We base our approach on an object detection model YOLOv8, preceded by a few steps: 1) filtering out irrelevant information, 2) enhancing the visibility of defects, namely brightness contrast, and 3) increasing the diversity of the training data through data augmentation. We evaluated the method in an industrial case study of crown wheel surface inspection in detecting Unclean Gear as well as Deburring defects, resulting in promising performances. With the combination of the three preprocessing steps, we improved the detection accuracy by 22.2% and 37.5% respectively while detecting those two defects. We believe that the proposed approach is also adaptable to various applications of surface defect detection in other industrial environments as the employed techniques, such as image segmentation, are available off the shelf.

Automatic Detection of Oil Palm Growth Rate Status with YOLOv5

Oil palm plantations are essential for Indonesia as a source of foreign exchange and a provider of employment opportunities. However, large-scale land clearing is considered a cause of deforestation, which harms the environment and society. So, it is necessary to manage plantations that are sustainable and still maintain the preservation of forests and biodiversity. One solution is to apply remote sensing technology. The research was conducted to develop a multi-class detection method for the growth rate of oil palm trees, with five categories: healthy palm, dead palm, yellowish palm, mismanaged palm, and smallish palm. The deep learning-based object detection method, YOLO Version 5 (YOLOv5), is used. This study compares the YOLOv5 network models, namely YOLOv5s, YOLOv5m, YOLOv5l, and YOLOv5x. Parameter setting is also carried out in the BCE (Binary Cross Entropy) with Logits Loss Function to handle the problem of unbalanced data distribution in each class. The YOLOv5 model with the highest mAP value is the YOLOv5l and YOLOv5x, the YOLOv5x requires longer training time. In this study, hyperparameter optimization was also carried out using hyperparameter evolution techniques. However, it has yet to provide increased results because the experiments conducted in this study are still limited.

Yolo Versions Architecture: Review

Deep learning techniques are used across a wide range of fields for several applications. In recent years, deep learning-based object detection from aerial or terrestrial photos has gained popularity as a study topic. The goal of object detection in computer vision is to anticipate the presence of one or more objects, along with their classes and bounding boxes. The YOLO (You Only Look Once) modern object detector can detect things in real-time with accuracy and speed. A neural network from the YOLO family of computer vision models makes one-time predictions about the locations of bounding rectangles andclassification probabilities for an image. In layman's terms, it is a technique for instantly identifying and recognizing items in images.This article, will be focusing on comparing the main differences among the YOLO version's Architecture, and will discuss its evolution from YOLO to YOLOv8, its network architecture, newfeatures, and applications. Itstarts by looking at the basic ideas and design of the first YOLO model, which laid the groundwork for the following improvements in the YOLO family. In additionally, this article will provide a step-by-step guide on how to use the YOLO version architecture, Understanding the primary drivers, feature development, constraints, and even relationships for the versions is crucial as the YOLO versions advance.Researchers interested in object detection, especially beginning researchers, would find this paper useful and enlightening

An efficient novel paradigm for object detection through web camera using deep learning (YOLOv5’s object detection model)

Object detection, a fundamental duty in computer vision that has a wide range of practical applications, they are surveillance, robotics, and autonomous driving. Recent developments of deep learning have got gradual improvemenrts in detection accuracy and speed. One of the most popular and effective deep learning models for object detection is YOLOv5. In this discussion, we an object detection model through YOLOv5 and its implementation for object detection tasks. We discuss the model’s architecture, training process, and evaluation metrics. Furthermore, we present experimental results on popular object detection benchmarks to demonstrate the efficacy and efficiency of YOLOv5 in detecting various objects in complex scenes. Our experiments states that YOLOv5 out performs other state of the art object detection models case of accuracy of detected image and speed of detection, making it a promising approach for real-world applications. Our work contributes to the growing body of research on deep learning-based object detection and provides valuable insights into the capabilities and limitations of YOLOv5. By improving accuracy, speed of object detection models, we have enabled a wide range of applications that can benefit society in countless ways.

Deep Learning-Based Object Detection and Holographic Virtual Imaging Technologies, Mobile Biometric and Sentiment Data, and Digital Twin Simulation and Modeling Tools in the Metaverse Economy

Deep Learning-Based Object Detection and Holographic Virtual Imaging Technologies, Mobile Biometric and Sentiment Data, and Digital Twin Simulation and Modeling Tools in the Metaverse Economy