Object Detection Model Research Articles

Lightweight object detection in low light: Pixel-wise depth refinement and TensorRT optimization

Images captured in low-light conditions present significant challenges for accurate object detection due to factors such as high noise, poor illumination, and low contrast. In this study, we propose an innovative approach that combines pixel-wise depth refinement and TensorRT optimization to improve object detection performance and inference speed under challenging lighting scenarios. The Pixel-wise depth refinement utilizes a deep learning model to estimate the depth curve for each pixel in the low-light image, providing detailed scene depth information. We used the Lightweight YOLOv8 object detection model using TensorRT. This will reduce the model's computational complexity and memory footprint, enabling faster inference and real-time performance on resource-constrained devices. By combining these techniques, our approach aims to accomplish enhanced entity recognition precision in reduced-illumination environments while maintaining efficiency and real-time performance. We evaluate the effectiveness of our proposed modifications to the depth curve estimation block and the overall approach on benchmark datasets and demonstrate its potential for enhancing object detection capabilities in challenging low-light conditions. Furthermore, the experimental results show an improvement in the precision, recall, and mean average precisions (mAP), and also by using the TensorRT the inference speed is four times faster than the existing one.

SOA: Seed point offset attention for indoor 3D object detection in point clouds

Three-dimensional object detection plays a pivotal role in scene understanding and holds significant importance in various indoor perception applications. Traditional methods based on Hough voting are susceptible to interference from background points or neighboring objects when casting votes for the target’s center from each seed point. Moreover, fixed-size set abstraction modules may result in the loss of structural information for large objects. To address these challenges, this paper proposes a three-dimensional object detection model based on seed point offset attention. The objective of this model is to enhance the model’s resilience to voting noise interference and alleviate feature loss for large-scale objects. Specifically, a seed point offset tensor is first defined, and then the offset tensor self-attention network is employed to learn the weights between votes, thereby establishing a correlation between the voting semantic features and the object structural information. Furthermore, an object surface perception module is introduced, which incorporates detailed features of local object surfaces into global feature representations through vote backtracking and surface mapping. Experimental results indicate that the model achieved excellent performance on the ScanNet-V2 (mAP@0.5, 60.3%) and SUN RGB-D (mAP@0.5, 64.0%) datasets, respectively improving by 2.6% (mAP@0.5) and 5.4% (mAP@0.5) compared to VoteNet.

FETR: Feature Transformer for vehicle-infrastructure cooperative 3D object detection

3D object detection plays a crucial role in the perception system of autonomous vehicles, however, the vehicle’s field of view is restricted due to obstructions from nearby vehicles and buildings. Vehicle-infrastructure cooperation can compensate for the issue of visibility, but due to discrepancies in timestamps between vehicle and infrastructure sensors as well as data transmission delays, there is typically a time asynchrony between vehicle and infrastructure data. Therefore, Feature Transformer (FETR) has been introduced, which is a vehicle-infrastructure cooperative 3D object detection model utilizing Transformer as a Feature Predictor. The Transformer Predictor is capable of predicting features of future frame based on the current frame features, efficiently addressing the problem of time asynchrony. Additionally, to enhance the precision of 3D object detection, we have introduced a plug-and-play module named Mask Feature Enhancement (MFE), MFE employs a mask to amplify the features in the object region while simultaneously diminishing the features of the surrounding environment, enlarging the difference between object features and environmental features, thereby improving the detection effect. Experimental results show that FETR attains a 68.15 BEV-mAP (IoU=0.5) on the DAIR-V2X dataset, with a 200ms latency, and the data transmission is merely 6.0×104 bytes, constituting just 4.2% of the original point cloud data, outperforming current vehicle-infrastructure cooperative models in terms of both precision and data transmission.

GCPDFFNet: Small Object Detection for Rice Blast Recognition.

Early detection of rice blast disease is pivotal to ensure rice yield. We collected in situ images of rice blast and constructed a rice blast dataset based on variations in lesion shape, size, and color. Given that rice blast lesions are small and typically exhibit round, oval, and fusiform shapes, we proposed a small object detection model named GCPDFFNet (global context-based parallel differentiation feature fusion network) for rice blast recognition. The GCPDFFNet model has three global context feature extraction modules and two parallel differentiation feature fusion modules. The global context modules are employed to focus on the lesion areas; the parallel differentiation feature fusion modules are used to enhance the recognition effect of small-sized lesions. In addition, we proposed the SCYLLA normalized Wasserstein distance loss function, specifically designed to accelerate model convergence and improve the detection accuracy of rice blast disease. Comparative experiments were conducted on the rice blast dataset to evaluate the performance of the model. The proposed GCPDFFNet model outperformed the baseline network CenterNet, with a significant increase in mean average precision from 83.6 to 95.4% on the rice blast test set while maintaining a satisfactory frames per second drop from 147.9 to 122.1. Our results suggest that the GCPDFFNet model can accurately detect in situ rice blast disease while ensuring the inference speed meets the real-time requirements.

Robust deep learning based shrimp counting in an industrial farm setting

Shrimp production is one of the fastest growing sectors in the aquaculture industry. Despite extensive research in recent years, stocking densities in shrimp systems still depend on manual sampling which is neither time nor cost efficient and additionally challenges shrimp welfare. This paper compares the performance of automatic shrimp counting solutions for commercial Recirculating Aquaculture System (RAS) based farming systems, using eight Deep Learning based methods. The entire dataset includes 1379 images of shrimps in RAS farming tanks, taken at a distance using an iPhone 11 mini. These were manually annotated, with bounding boxes for every clearly visible shrimp. The dataset was partitioned into training (60 %, 828 samples), validation (20 %, 276 samples) and test (20 %, 275 samples) splits for purposes of training and evaluating the models. The present work demonstrates that state-of-the-art object detection models outperform manual counting and achieve high performance across the entire production range and at various circumstances known to be challenging for object detection (dim light, overlapping and small animals, various acquisition devices and image resolutions and camera distance to object). Highest counting performance was obtained with models based on YOLOv5m6 and Faster R–CNN (as opposed to neural network autoencoder architecture to estimate a density map). The best model generalizes well on an independent test set and even shows promising performance when tested with different taxa. The model performs best at densities below 200 shrimps per image with an overall error of 5.97 %. It is assumed that this performance can be improved by increasing the dataset size, especially with images at high shrimp stocking density, and it is strongly believed that a performance below the 5 % error threshold is close to being achieved, which will allow for deployment of the model in an industrial setting.

Artificial immune systems for data augmentation

We study object detection models and observe that their respective architectures are vulnerable to image distortions such as noise, compression, blur, or snow. We propose alleviating this problem by training the models with antibodies generated using Artificial Immune Systems (AIS) from original training samples (antigens). These antibodies are AIS-distorted antigens at the pixel level through cycles of “select, clone, mutate, select” until an affinity to the antigen is achieved. We then add the antibodies to the antigens, train the models, validate and test them under 15 distortions, and show that our data augmentation approach (AISbod) significantly improved their accuracy without altering their architecture or inference speed. For example, the DINO object detector under the COCO dataset improves by 4% under clean samples, by 6.50% on average over all 15 distortions, by 2.15% under snow, and by 27.60% under impulse noise. Our simulations show that our method performs better under distortions and clean samples than related defense methods and is more consistent across datasets and object detection models. For instance, our method is, on average, 70% better than the closest related method across 15 distortions for the evaluated models under COCO. Moreover, we show that our approach to image classification and object tracking models significantly improves accuracy under distortions. We provide the code of our method and the DINO model trained using our method at https://github.com/moforio/AISbod.

Development of a multi-level feature fusion model for basketball player trajectory tracking

To solve the problems of low matching degree, long tracking time, and low accuracy of multi-target tracking in the process of athlete motion trajectory tracking using deep learning technology, a new athlete motion trajectory tracking model was proposed in this study. The study first optimized the current object detection algorithm in basketball, utilized a hybrid attention mechanism to extract object features, and improved the non-maximum suppression strategy. Then, a hybrid branch network was introduced to improve the residual network and a new athlete identity recognition model was proposed. Finally, a new trajectory tracking model was designed by combining the object detection model and the athlete identity recognition model. The research results indicated that in the object detection experiment, the detection time of the proposed object detection algorithm was always below 0.4 s, and its average accuracy reached up to 0.63. In trajectory tracking testing, the final built tracking model had a multi-target tracking accuracy of up to 0.98, and its tracking overlap rate was as low as 0.02. This study has the following two contributions. Firstly, a new model of athlete trajectory tracking is proposed, which improves the accuracy and efficiency of multi-target tracking by optimizing object detection algorithm and introducing hybrid branch network. Second, the model has excellent performance in both object detection and track tracking, which can not only provide a new solution for athletes' motion trajectory tracking, but also significantly improve the effect of motion tracking.

ALdamage-seg: A Lightweight Model for Instance Segmentation of Aluminum Profiles

Aluminum profiles are widely used in various manufacturing sectors due to their flexibility and chemical properties. However, these profiles are susceptible to defects during manufacturing and transportation. Detecting these defects is crucial, but existing object detection models like Mask R-CNN and YOLOv8-seg are not optimized for this task. These models are large and computationally intensive, making them unsuitable for edge devices used in industrial inspections. To address this issue, this study proposes a novel lightweight instance segmentation model called AL-damage-seg, inspired by the YOLOv8n-seg architecture. This model utilizes MobileNetV3 as the backbone. In YOLOv8n-seg, the role of C2f is to enhance the nonlinear representation of the model to capture complex image features more efficiently. We upgraded and improved it to form multilayer feature extraction module (MFEM) and integrates a large separable kernel attention (LSKA) mechanism in the C2f module, resulting in C2f_LSKA, to further optimize the performance of the model. Additionally, depth-wise separable convolutions are employed in the feature fusion process. The ALdamage-seg’s weight on the Alibaba Tian-chi aluminum profile dataset constitutes 43.9% of that of YOLOv8n-seg, with its GFLOPs reduced to 53% relative to YOLOv8-seg, all the while achieving an average precision (mAP) of 99% relative to YOLOv8-seg. With its compact size and lower computational requirements, this model is well-suited for deployment on edge devices with limited processing capabilities.

Wind turbine blade defect detection with a semi-supervised deep learning framework

To increase the economic efficiency of utilizing wind turbines, an enhanced object detection model based on the small version of the fifth generation of the You Look Only Once algorithm (YOLOv5s) is proposed in this paper, which can effectively detect cracks on the surface of wind turbine blades using images captured by unmanned aerial vehicles. To improve the extraction of light-colored and low-definition images, Omni-Dimensional Dynamic Convolution (ODConv) and Dynamic Head Module components (DyHead) are introduced in the proposed method, while a lightweight Group Shuffle convolution (GSConv) module is utilized to accelerate the model inference speed without sacrificing detection performance. Furthermore, a semi-supervised learning strategy is developed to reduce human labors in annotating images. Extensive experiments demonstrate that the proposed model outperforms the original YOLOv5s in terms of both detection accuracy and inference speed. Besides, the proposed model has good performance against state-of-the-art methods. Furthermore, the experiments validate the efficacy of the proposed semi-supervised learning strategy.

A Study on GAN-Based Car Body Part Defect Detection Process and Comparative Analysis of YOLO v7 and YOLO v8 Object Detection Performance

The main purpose of this study is to generate defect images of body parts using a GAN (generative adversarial network) and compare and analyze the performance of the YOLO (You Only Look Once) v7 and v8 object detection models. The goal is to accurately judge good and defective products. Quality control is very important in the automobile industry, and defects in body parts directly affect vehicle safety, so the development of highly accurate defect detection technology is essential. This study ensures data diversity by generating defect images of car body parts using a GAN and through this, compares and analyzes the object detection performance of the YOLO v7 and v8 models to present an optimal solution for detecting defects in car parts. Through experiments, the dataset was expanded by adding fake defect images generated by the GAN. The performance experiments of the YOLO v7 and v8 models based on the data obtained through this approach demonstrated that YOLO v8 effectively identifies objects even with a smaller amount of data. It was confirmed that defects could be detected. The readout of the detection system can be improved through software calibration.

EMG-YOLO: road crack detection algorithm for edge computing devices.

Road cracks significantly shorten the service life of roads. Manual detection methods are inefficient and costly. The YOLOv5 model has made some progress in road crack detection. However, issues arise when deployed on edge computing devices. The main problem is that edge computing devices are directly connected to sensors. This results in the collection of noisy, poor-quality data. This problem adds computational burden to the model, potentially impacting its accuracy. To address these issues, this paper proposes a novel road crack detection algorithm named EMG-YOLO. First, an Efficient Decoupled Header is introduced in YOLOv5 to optimize the head structure. This approach separates the classification task from the localization task. Each task can then focus on learning its most relevant features. This significantly reduces the model's computational resources and time. It also achieves faster convergence rates. Second, the IOU loss function in the model is upgraded to the MPDIOU loss function. This function works by minimizing the top-left and bottom-right point distances between the predicted bounding box and the actual labeled bounding box. The MPDIOU loss function addresses the complex computation and high computational burden of the current YOLOv5 model. Finally, the GCC3 module replaces the traditional convolution. It performs global context modeling with the input feature map to obtain global context information. This enhances the model's detection capabilities on edge computing devices. Experimental results show that the improved model has better performance in all parameter indicators compared to current mainstream algorithms. The EMG-YOLO model improves the accuracy of the YOLOv5 model by 2.7%. The mAP (0.5) and mAP (0.9) are improved by 2.9% and 0.9%, respectively. The new algorithm also outperforms the YOLOv5 model in complex environments on edge computing devices. The EMG-YOLO algorithm proposed in this paper effectively addresses the issues of poor data quality and high computational burden on edge computing devices. This is achieved through optimizing the model head structure, upgrading the loss function, and introducing global context modeling. Experimental results demonstrate significant improvements in both accuracy and efficiency, especially in complex environments. Future research can further optimize this algorithm and explore more lightweight and efficient object detection models for edge computing devices.

The object detection model uses combined extraction with KNN and RF classification

Object detection plays an important role in various fields. Developing detection models for 2D objects that experience rotation and texture variations is a challenge. In this research, the initial stage of the proposed model integrates the gray-level co-occurrence matrix (GLCM) and local binary patterns (LBP) texture feature extraction to obtain feature vectors. The next stage is classifying features using k-nearest neighbors (KNN) and random forest (RF), as well as voting ensemble (VE). System testing used a dataset of 4,437 2D images, the results for KNN accuracy were 92.7% and F1-score 92.5%, while RF performance was lower. Although GLCM features improve performance on both algorithms, KNN is more consistent. The VE approach provides the best performance with an accuracy of 93.9% and an F1-score of 93.8%, this shows the effectiveness of the ensemble technique in increasing object detection accuracy. This study contributes to the field of object detection with a new approach combining GLCM and LBP as feature vectors as well as VE for classification.

Automated Identification of Pavement Structural Distress Using State-of-the-Art Object Detection Models and Nondestructive Testing

Automated Identification of Pavement Structural Distress Using State-of-the-Art Object Detection Models and Nondestructive Testing

Automated Neutrophil Quantification and Histological Score Estimation in Ulcerative Colitis

Background and AimsIn the management of ulcerative colitis (UC), histological remission is increasingly recognized as the ultimate goal. The absence of neutrophil infiltration is crucial for assessing remission. This study aimed to develop an artificial intelligence (AI) system capable of accurately quantifying and localizing neutrophils in UC biopsy specimens to facilitate histological assessment. MethodsOur AI system, which incorporates semantic segmentation and object detection models, was developed to identify neutrophils in hematoxylin-eosin-stained whole slide images. The system assessed the presence and location of neutrophils within either the epithelium or lamina propria and predicted components of the Nancy Histological Index (NHI) and the PICaSSO Histologic Remission Index (PHRI). We evaluated the system’s performance against that of experienced pathologists and validated its ability to predict future clinical relapse risk in patients with clinically remitted UC. The primary outcome measure was the clinical relapse rate, defined as a partial Mayo score of ≥3. ResultsThe model accurately identified neutrophils, achieving a performance of 0.77, 0.81, and 0.79 for precision, recall, and F-score, respectively. The system’s histological score predictions showed a positive correlation with the pathologists’ diagnoses (Spearman’s ρ = 0.68–0.80, P < .05). Among patients who relapsed, the mean number of neutrophils in the rectum was higher than in those who did not relapse. Furthermore, the study highlighted that higher AI-based PHRI and NHI scores were associated with hazard ratios increasing from 3.2 to 5.0 for evaluating the risk of UC relapse. ConclusionThe AI system’s precise localization and quantification of neutrophils proved valuable for histological assessment and clinical prognosis stratification.

Automated Left Ventricle Segmentation in Echocardiography Using YOLO: A Deep Learning Approach for Enhanced Cardiac Function Assessment

Accurate segmentation of the left ventricle (LV) using echocardiogram (Echo) images is essential for cardiovascular analysis. Conventional techniques are labor-intensive and exhibit inter-observer variability. Deep learning has emerged as a powerful tool for automated medical image segmentation, offering advantages in speed and potentially superior accuracy. This study explores the efficacy of employing a YOLO (You Only Look Once) segmentation model for automated LV segmentation in Echo images. YOLO, a cutting-edge object detection model, achieves exceptional speed–accuracy balance through its well-designed architecture. It utilizes efficient dilated convolutional layers and bottleneck blocks for feature extraction while incorporating innovations like path aggregation and spatial attention mechanisms. These attributes make YOLO a compelling candidate for adaptation to LV segmentation in Echo images. We posit that by fine-tuning a pre-trained YOLO-based model on a well-annotated Echo image dataset, we can leverage the model’s strengths in real-time processing and precise object localization to achieve robust LV segmentation. The proposed approach entails fine-tuning a pre-trained YOLO model on a rigorously labeled Echo image dataset. Model performance has been evaluated using established metrics such as mean Average Precision (mAP) at an Intersection over Union (IoU) threshold of 50% (mAP50) with 98.31% and across a range of IoU thresholds from 50% to 95% (mAP50:95) with 75.27%. Successful implementation of YOLO for LV segmentation has the potential to significantly expedite and standardize Echo image analysis. This advancement could translate to improved clinical decision-making and enhanced patient care.

A New Multi-Branch Convolutional Neural Network and Feature Map Extraction Method for Traffic Congestion Detection.

With the continuous advancement of the economy and technology, the number of cars continues to increase, and the traffic congestion problem on some key roads is becoming increasingly serious. This paper proposes a new vehicle information feature map (VIFM) method and a multi-branch convolutional neural network (MBCNN) model and applies it to the problem of traffic congestion detection based on camera image data. The aim of this study is to build a deep learning model with traffic images as input and congestion detection results as output. It aims to provide a new method for automatic detection of traffic congestion. The deep learning-based method in this article can effectively utilize the existing massive camera network in the transportation system without requiring too much investment in hardware. This study first uses an object detection model to identify vehicles in images. Then, a method for extracting a VIFM is proposed. Finally, a traffic congestion detection model based on MBCNN is constructed. This paper verifies the application effect of this method in the Chinese City Traffic Image Database (CCTRIB). Compared to other convolutional neural networks, other deep learning models, and baseline models, the method proposed in this paper yields superior results. The method in this article obtained an F1 score of 98.61% and an accuracy of 98.62%. Experimental results show that this method effectively solves the problem of traffic congestion detection and provides a powerful tool for traffic management.

Design and implementation of deep learning-based object detection and tracking system

Many human tracking methods by deep learning rely on powerful computing resources. For embedded platforms with limited resources, efficient use of resources is a priority. In this paper, we design an object detection and tracking system based on deep learning methods. We propose an efficient system with software and hardware design. We apply the framework of Vitis AI and its Deep Learning Processing Unit using a hardware/software co-design approach. This approach capitalizes on a higher-level acceleration design framework, where the convolutional models can be updated more flexibly and rapidly. This design approach not only provides a fast design flow but also has good performance in terms of throughput. We facilitate the design and accelerate the object detection model YOLO v3 to achieve higher throughput and energy efficiency. Our tracking method achieves a 1.27x improvement in processing speed with the addition of a single-object tracker. Our proposed human tracking methods can achieve better performance than the others in precision with the same test sequences.

Evaluation of YOLOv8 Model Series with HOP for Object Detection in Complex Agriculture Domains

In recent years, many studies have been conducted in-depth investigating YOLO Models for object detection in the field of agriculture. For this reason, this study focused on four datasets containing different agricultural scenarios, and 20 dif-ferent trainings were carried out with the objectives of understanding the detec-tion capabilities of YOLOv8 and HPO (optimization of hyperparameters). While Weed/Crop and Pineapple datasets reached the most accurate measurements with YOLOv8n in mAP score of 0.8507 and 0.9466 respectively, the prominent model for Grapes and Pear datasets was YOLOv8l in mAP score of 0.6510 and 0.9641. This situation shows that multiple-species or in different developmental stages of a single species object YOLO training highlights YOLOv8n, while only object detection extracting from background scenario naturally highlights YOLOv8l Model.

Fish-NET: Advancing Aquaculture Management through AI-Enhanced Fish Monitoring and Tracking

This study seeks to enhance aquaculture and fishery management using artificial intelligence, focusing on Nigerian catfish farming. The methodology encompasses a sequence of steps from data collection to validation. A dataset, primarily composed of aerial imagery from catfish ponds and supplemented with additional data from the internet, formed the foundation of this research. By leveraging computer vision and deep learning techniques, the data were processed to assess the potential of the three distinct cutting-edge object detection models. Based on various evaluation metrics to gauge their effectiveness in fish detection tasks, the Faster R-CNN emerged as the optimal model, boasting a superior balance of precision and recall. This model was subsequently integrated with an object-tracking model and deployed as an application, yielding promising results in terms of fish detection and tracking. The findings in this study suggest that AI-driven tools can automate monitoring processes, significantly increasing accuracy and efficiency in resource utilization.

YOLO-Based Personal Protective Equipment Monitoring System for Workplace Safety

Occupational health and safety are of paramount importance in industrial environments and various work fields. In this context, tracking personal protective equipment (PPE) is highly necessary. This article investigates the performance and application of deep learning-based object detection models to enhance the accuracy and speed of tracking personal protective equipment for ensuring occupational health and safety. These models detect personal protective equipment in images, enabling monitoring of their correct usage and intervention when necessary. The study aims to minimize damage resulting from accidents through the use of protective equipment and to prevent possible accidents. In our study, a dataset consisting of 2581 images, encompassing different workplace environments and workers, was prepared. This dataset was evaluated for performance using deep learning models. Popular deep-learning models such as YOLO-NAS, YOLOv8, and YOLOv9 were utilized in the comparisons. During the training of the models, the number of epochs was kept consistent for fair comparison. Upon examining the results, it is observed that the YOLO-NAS and YOLOv9 models generally exhibit similar and high performance.