Object Detection Model Research Articles

YOLO-MMS for aerial object detection model based on hybrid feature extractor and improved multi-scale prediction

YOLO-MMS for aerial object detection model based on hybrid feature extractor and improved multi-scale prediction

KOALA: A Modular Dual-Arm Robot for Automated Precision Pruning Equipped with Cross-Functionality Sensor Fusion

Landscape maintenance is essential for ensuring agricultural productivity, promoting sustainable land use, and preserving soil and ecosystem health. Pruning is a labor-intensive task among landscaping applications that often involves repetitive pruning operations. To address these limitations, this paper presents the development of a dual-arm holonomic robot (called the KOALA robot) for precision plant pruning. The robot utilizes a cross-functionality sensor fusion approach, combining light detection and ranging (LiDAR) sensor and depth camera data for plant recognition and isolating the data points that require pruning. The You Only Look Once v8 (YOLOv8) object detection model powers the plant detection algorithm, achieving a 98.5% pruning plant detection rate and a 95% pruning accuracy using camera, depth sensor, and LiDAR data. The fused data allows the robot to identify the target boxwood plants, assess the density of the pruning area, and optimize the pruning path. The robot operates at a pruning speed of 10–50 cm/s and has a maximum robot travel speed of 0.5 m/s, with the ability to perform up to 4 h of pruning. The robot’s base can lift 400 kg, ensuring stability and versatility for multiple applications. The findings demonstrate the robot’s potential to significantly enhance efficiency, reduce labor requirements, and improve landscape maintenance precision compared to those of traditional manual methods. This paves the way for further advancements in automating repetitive tasks within landscaping applications.

Fruit Distribution Density Estimation in YOLO-Detected Strawberry Images: A Kernel Density and Nearest Neighbor Analysis Approach

Precise information on strawberry fruit distribution is of significant importance for optimizing planting density and formulating harvesting strategies. This study applied a combined analysis of kernel density estimation and nearest neighbor techniques to estimate fruit distribution density from YOLOdetected strawberry images. Initially, an improved yolov8n strawberry object detection model was employed to obtain the coordinates of the fruit centers in the images. The results indicated that the improved model achieved an accuracy of 94.7% with an mAP@0.5~0.95 of 87.3%. The relative error between the predicted and annotated coordinates ranged from 0.002 to 0.02, demonstrating high consistency between the model predictions and the annotated results. Subsequently, based on the strawberry center coordinates, the kernel density estimation algorithm was used to estimate the distribution density in the strawberry images. The results showed that with a bandwidth of 200, the kernel density estimation accurately reflected the actual strawberry density distribution, ensuring that all center points in high-density regions were consistently identified and delineated. Finally, to refine the strawberry distribution information, a comprehensive method based on nearest neighbor analysis was adopted, achieving target area segmentation and regional density estimation in the strawberry images. Experimental results demonstrated that when the distance threshold ϵ was set to 600 pixels, the correct grouping rate exceeded 94%, and the regional density estimation results indicated a significant positive correlation between the number of fruits and regional density. This study provides scientific evidence for optimizing strawberry planting density and formulating harvesting sequences, contributing to improved yield, harvesting efficiency, and reduced fruit damage. In future research, this study will further explore dynamic models that link fruit distribution density, planting density, and fruit growth status.

Investigating the Sim-to-Real Generalizability of Deep Learning Object Detection Models.

State-of-the-art object detection models need large and diverse datasets for training. As these are hard to acquire for many practical applications, training images from simulation environments gain more and more attention. A problem arises as deep learning models trained on simulation images usually have problems generalizing to real-world images shown by a sharp performance drop. Definite reasons and influences for this performance drop are not yet found. While previous work mostly investigated the influence of the data as well as the use of domain adaptation, this work provides a novel perspective by investigating the influence of the object detection model itself. Against this background, first, a corresponding measure called sim-to-real generalizability is defined, comprising the capability of an object detection model to generalize from simulation training images to real-world evaluation images. Second, 12 different deep learning-based object detection models are trained and their sim-to-real generalizability is evaluated. The models are trained with a variation of hyperparameters resulting in a total of 144 trained and evaluated versions. The results show a clear influence of the feature extractor and offer further insights and correlations. They open up future research on investigating influences on the sim-to-real generalizability of deep learning-based object detection models as well as on developing feature extractors that have better sim-to-real generalizability capabilities.

A Real-Time Semantic Map Production System for Indoor Robot Navigation.

Although grid maps help mobile robots navigate in indoor environments, some lack semantic information that would allow the robot to perform advanced autonomous tasks. In this paper, a semantic map production system is proposed to facilitate indoor mobile robot navigation tasks. The developed system is based on the employment of LiDAR technology and a vision-based system to obtain a semantic map with rich information, and it has been validated using the robot operating system (ROS) and you only look once (YOLO) v3 object detection model in simulation experiments conducted in indoor environments, adopting low-cost, -size, and -memory computers for increased accessibility. The obtained results are efficient in terms of object recognition accuracy, object localization error, and semantic map production precision, with an average map construction accuracy of 78.86%.

Object detection model with efficient feature extraction and asymptotic feature fusion for unmanned aerial vehicle image

Object detection model with efficient feature extraction and asymptotic feature fusion for unmanned aerial vehicle image

On-Tree Mango Fruit Count Using Live Video- Split Image Dataset to Predict Better Yield at Pre-Harvesting Stage

This study introduces a method for fruit counting in agricultural settings using video capture and the YOLOv7 object detection model. By splitting captured videos into frames and strategically selecting representative frames, the approach aims to accurately estimate fruit counts while minimizing the risk of double counting. YOLOv7, known for its efficiency and accuracy in object detection, is employed to analyze selected frames and detect fruits on trees. Demonstrated the method's effectiveness through its ability to provide farmers with precise yield estimations, optimize resource management, and facilitate early detection of orchard issues such as pest infestations or nutrient deficiencies. This technological integration reduces labor costs and supports sustainable agricultural practices by improving productivity and decision-making capabilities. The scalability of the approach makes it suitable for diverse orchard sizes and types, offering a promising tool for enhancing agricultural efficiency and profitability. The researcher compared YOLOv5n, YOLOv5s, YOLOv7, and YOLOv7-tiny with eight-sided imaging techniques around the tree. The experimental results of YOLOv7 with the eight-sided technique performed best and achieved a count accuracy of 97.7% on a single tree in just 17.112 ms of average inference time. On multiple trees, it is 95.48% in just 17 ms of average inference time, with the help of an eight- sided method on tree images.

AI-Powered Identification of Osteoporosis in Dental Panoramic Radiographs: Addressing Methodological Flaws in Current Research.

Background: Osteoporosis, a systemic skeletal disorder, is expected to affect 60% of women over 50. While dual-energy X-ray absorptiometry (DXA) scans are the current gold standard for diagnosis, they are typically used only after fractures occur, highlighting the need for early detection tools. Initial studies have shown panoramic radiographs (PRs) to be a potential medium, but these have methodological flaws. This study aims to address these shortcomings by developing a robust AI application for accurate osteoporosis identification in PRs. Methods: A total of 348 PRs were used for development, 58 PRs for validation, and 51 PRs for hold-out testing. Initially, the YOLOv8 object detection model was employed to predict the regions of interest. Subsequently, the predicted regions of interest were extracted from the PRs and processed by the EfficientNet classification model. Results: The model for osteoporosis detection on a PR achieved an overall sensitivity of 0.83 and an F1-score of 0.53. The area under the curve (AUC) was 0.76. The lowest detection sensitivity was for the cropped angulus region (0.66), while the highest sensitivity was for the cropped mental foramen region (0.80). Conclusion: This research presents a proof-of-concept algorithm showing the potential of deep learning to identify osteoporosis in dental radiographs. Furthermore, our thorough evaluation of existing algorithms revealed that many optimistic outcomes lack credibility when subjected to rigorous methodological scrutiny.

UAV imagery, advanced deep learning, and YOLOv7 object detection model in enhancing citrus yield estimation

UAV imagery, advanced deep learning, and YOLOv7 object detection model in enhancing citrus yield estimation

ASOD: An Atrous Object Detection Model Using Multiple Attention Mechanisms for Obstacle Detection in Intelligent Connected Vehicles

ASOD: An Atrous Object Detection Model Using Multiple Attention Mechanisms for Obstacle Detection in Intelligent Connected Vehicles

Object Detection for Indoor Localization System

Indoor localization systems have gained significant attention in recent years due to their applications in various fields such as smart homes, retail environments, and healthcare facilities. This paper presents an innovative approach to indoor localization through the integration of object detection techniques, aiming to enhance accuracy and efficiency in identifying and locating objects within indoor spaces. We explore the use of advanced deep learning algorithms, particularly convolutional neural networks (CNNs), to detect and classify objects in real-time. Our methodology involves collecting a comprehensive dataset of indoor environments, training a robust object detection model, and implementing it in a localization framework that utilizes both visual and spatial data. The experimental results demonstrate that our proposed system achieves high detection accuracy and reduced localization errors, outperforming traditional methods. Furthermore, we discuss the potential of leveraging object recognition to improve user experience and navigation in complex indoor settings. This research contributes to the evolving field of indoor localization and offers a foundation for future developments in intelligent indoor navigation systems.

Deep learning for diagnostic charting on pediatric panoramic radiographs.

Artificial intelligence (AI)-based systems are used in dentistry to ensure a more accurate and efficient diagnostic process. The objective of the present study was to evaluate the performance of a deep learning (DL) program for the detection and classification of dental structures and treatments on panoramic radiographs of pediatric patients. In total, 4821 anonymized digital panoramic radiographs of children between 5 and 13 years of age were analyzed by YOLOv4, a CNN (Convolutional Neural Networks)-based object detection model. The ability to make a correct diagnosis was tested on samples from pediatric patients examined within the scope of the study. All statistical analyses were performed using SPSS version 26.0 software. The YOLOv4 model diagnosed the primary teeth, permanent tooth germs, and brackets successfully, with high F1 scores of 0.95, 0.90, and 0.76, respectively. Although this model achieved promising results, there were certain limitations for some dental structures and treatments, including fillings, root canal treatments, and supernumerary teeth. The architecture of the present study achieved reliable results, with some specific limitations for detecting dental structures and treatments. The detection of certain dental structures and previous dental treatments on pediatric panoramic radiographs by using a DL-based approach may provide early diagnosis of some dental anomalies and help dental practitioners to find more accurate treatment options by saving time and effort.

Visual object detection model integrating deep active learning

The perception of surrounding objects by vehicle autonomous driving is an important means to ensure traffic safety. Object detection models based on deep learning are widely used, but they require a large amount of labeled data for training. This paper proposes an active visual object detection model that uses Gaussian mixture distribution to estimate the uncertainty of unlabeled images, reducing the dependence of model training on labeled data. First, a mixed density network is used as the detection head, and the image features extracted by the deep neural network are used as input to estimate the probability distribution of the classification and positioning of the target prediction box. Secondly, the classification score value of the target prediction box is mapped to the probability space, and the classification uncertainty of the target is calculated using the edge uncertainty; the positioning uncertainty of the target is measured using the prediction box positioning variance. Finally, the most unstable samples are selected for labeling. Compared with other typical active learning sampling strategies on the VOC dataset, the proposed method achieves the best performance, and the 54%data annotation amount can reach the performance of YOLOX supervised learning 98.8%, saving nearly 45% of the data annotation amount.

Intelligent Vision System with Pruning and Web Interface for Real-Time Defect Detection on African Plum Surfaces

Agriculture stands as the cornerstone of Africa’s economy, supporting over 60% of the continent’s labor force. Despite its significance, the quality assessment of agricultural products remains a challenging task, particularly at a large scale, consuming valuable time and resources. The African plum is an agricultural fruit that is widely consumed across West and Central Africa but remains underrepresented in AI research. In this paper, we collected a dataset of 2892 African plum samples from fields in Cameroon representing the first dataset of its kind for training AI models. The dataset contains images of plums annotated with quality grades. We then trained and evaluated various state-of-the-art object detection and image classification models, including YOLOv5, YOLOv8, YOLOv9, Fast R-CNN, Mask R-CNN, VGG-16, DenseNet-121, MobileNet, and ResNet, on this African plum dataset. Our experimentation resulted in mean average precision scores ranging from 88.2% to 89.9% and accuracies between 86% and 91% for the object detection models and the classification models, respectively. We then performed model pruning to reduce model sizes while preserving performance, achieving up to 93.6% mean average precision and 99.09% accuracy after pruning YOLOv5, YOLOv8 and ResNet by 10–30%. We deployed the high-performing YOLOv8 system in a web application, offering an accessible AI-based quality assessment tool tailored for African plums. To the best of our knowledge, this represents the first such solution for assessing this underrepresented fruit, empowering farmers with efficient tools. Our approach integrates agriculture and AI to fill a key gap.

BEW-YOLOv8: A deep learning model for multi-scene and multi-scale flood depth estimation

As global climate change intensifies, the frequency of extreme weather events, including urban flooding, has risen, posing a significant threat to the safety of urban areas. Efficient and precise flood depth monitoring is crucial for a dynamic understanding of disaster conditions, enabling informed decision-making and reducing the potential for significant loss of life and property. Although object detection models have shown promise in estimating flood depths and have achieved notable results, enhancements are still needed in applications across multi-scene and multi-scale. This research enhances the YOLOv8 model by integrating Bidirectional Feature Pyramid Network (BiFPN), Effective Squeeze and Excitation (EffectiveSE), and Wise-IoU (WIoU), targeting submerged cars to develop the BEW-YOLOv8 model. Testing shows that the BEW-YOLOv8 model improves Precision, Recall, F1 Score, mAP@0.5, and mAP@0.5–0.95 by 14.1%, 2.2%, 7.9%, 8.7%, and 6.3%, respectively, compared to the unmodified YOLOv8 model. Compared with other existing models, BEW-YOLOv8 achieves the best performance with less than one-tenth of the parameters. Furthermore, this study verifies that the BEW-YOLOv8 model holds considerable promise for further enhancements with dataset expansions. Its precision and dependability make the BEW-YOLOv8 model well-suited for real-time flood depth assessment across multiple scenes and scales. The model’s capability for real-time processing supports urgent flood response needs, offering solid technical assistance for managing urban floods and mitigating disaster risks.

Building usage prediction in complex urban scenes by fusing text and facade features from street view images using deep learning

Building usage maps are inputs to many urban planning applications, however, the existing methods and the available data have limitations in generating instance-level high-resolution usage maps. In this study we tackle this problem by utilizing Street View Images (SVIs) and proposing a novel ensemble learning architecture that leverages building facade features and text extracted from hoardings, posters, etc. on buildings to predict the usage class. A pre-trained object detection model i.e., Grounding DINO, is implemented to efficiently identify buildings. A novel manually labeled training data of detected buildings corresponding to their usage is used to extract features from building facades across diverse Indian cities (Hyderabad, Mumbai, Bangalore, Delhi) using Vision Transformer (ViT) model. Following this, CLIPSeg a pre-trained segmentation model is used to recognizes text specifically on building elements like signs, posters, and banners. We then leverage GPT-3.5 Turbo, a Large Language Model (LLM), fine-tuned with a specifically designed few-shot prompting method, to infer building usage from the recognized text. To achieve optimal performance, the proposed ensemble linear metaclassifier combines predictions from ViT and LLM model. The predicted building usages are attributed to their corresponding locations to develop spatial maps. An analysis of our framework compared against ground truth data collected from various Indian cities reveals significantly accurate outcomes. Our findings highlight the utility of textual information in classifying utilities and commercial buildings, while features extracted from vision models prove more informative for residential buildings. Our approach can automate the generation of roadside building attributes and usage details on a larger scale.

MCH-PAN: gastrointestinal polyp detection model integrating multi-scale feature information.

The rise of object detection models has brought new breakthroughs to the development of clinical decision support systems. However, in the field of gastrointestinal polyp detection, there are still challenges such as uncertainty in polyp identification and inadequate coping with polyp scale variations. To address these challenges, this paper proposes a novel gastrointestinal polyp object detection model. The model can automatically identify polyp regions in gastrointestinal images and accurately label them. In terms of design, the model integrates multi-channel information to enhance the ability and robustness of channel feature expression, thus better coping with the complexity of polyp structures. At the same time, a hierarchical structure is constructed in the model to enhance the model's adaptability to multi-scale targets, effectively addressing the problem of large-scale variations in polyps. Furthermore, a channel attention mechanism is designed in the model to improve the accuracy of target positioning and reduce uncertainty in diagnosis. By integrating these strategies, the proposed gastrointestinal polyp object detection model can achieve accurate polyp detection, providing clinicians with reliable and valuable references. Experimental results show that the model exhibits superior performance in gastrointestinal polyp detection, which helps improve the diagnostic level of digestive system diseases and provides useful references for related research fields.

An Automated Clubbed Fingers Detection System Based on YOLOv8 and U-Net: A Tool for Early Prediction of Lung and Cardiovascular Diseases

Background/Objectives: Lung and cardiovascular diseases are leading causes of mortality worldwide, yet early detection remains challenging due to the subtle symptoms. Digital clubbing, characterized by the bulbous enlargement of the fingertips, serves as an early indicator of these diseases. This study aims to develop an automated system for detecting digital clubbing using deep-learning models for real-time monitoring and early intervention. Methods: The proposed system utilizes the YOLOv8 model for object detection and U-Net for image segmentation, integrated with the ESP32-CAM development board to capture and analyze finger images. The severity of digital clubbing is determined using a custom algorithm based on the Lovibond angle theory, categorizing the condition into normal, mild, moderate, and severe. The system was evaluated using 1768 images and achieved cloud-based and real-time processing capabilities. Results: The system demonstrated high accuracy (98.34%) in real-time detection with precision (98.22%), sensitivity (99.48%), and specificity (98.22%). Cloud-based processing achieved slightly lower but robust results, with an accuracy of 96.38%. The average processing time was 0.15 s per image, showcasing its real-time potential. Conclusions: This automated system provides a scalable and cost-effective solution for the early detection of digital clubbing, enabling timely intervention for lung and cardiovascular diseases. Its high accuracy and real-time capabilities make it suitable for both clinical and home-based health monitoring.

SOD‐YOLO: Small Object Detection Network for UAV Aerial Images

With the rapid development of the UAV industry, object detection using UAV has become a research hotspot. However, most current object detection models based on deep learning have large parameter counts and are difficult to deploy on embedded devices with limited memory and computational power. To address this problem, a Small Object Detection network for UAV aerial images SOD‐YOLO based on YOLOv8 is proposed, which can meet the application requirements of resource‐constrained devices while ensuring the detection accuracy. First, cross‐domain fusion attention (CDFA) mechanism is proposed to build the C2f‐Attention module in this paper, which is embedded in the backbone network in order to improve the extraction capability of key object features. Meanwhile, the AIFI_LSPE feature fusion module with improved RT‐DETR and the IoU‐aware query selection mechanism are added to the path aggregation network to improve the accuracy of multi‐scale object detection. In addition, in order to balance the sample size ratio and improve the robustness of the network model, we make a new UAV image dataset named VisDrone2019 Extended Edition (VDEE) using images from the VisDrone2019 and UAVDT public datasets. Finally, Shape‐IoU is used as a loss function to reduce the difference between the object GT frame and the detection frame. Experiments show that SOD‐YOLO has a mAP@0.5 of 42.8% in the VDEE dataset, which is increased by 5.1% over YOLOv8. In the VisDrone2019 dataset mAP@0.5 is 39.2%, an improvement of 5.8% over YOLOv8. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Enhancing detection accuracy of highly overlapping targets in agricultural imagery using IoA-SoftNMS algorithm across diverse image sizes

Object detection is crucial for agricultural monitoring and agriculture automation, yet conventional non-maximum suppression (NMS) algorithms often struggle in agricultural scenes with complex backgrounds and highly overlapping targets, especially in intersection over union (IoU) threshold setting and abnormal non-maximum removal. This study proposed the soft non-maximum suppression based on intersection over area (IoA-SoftNMS) algorithm, an advanced NMS algorithm designed to enhance detection accuracy in such challenging agricultural environments. IoA-SoftNMS employs intersection over area (IoA) to quantify overlap and integrate SoftNMS to boost overall detection precision and effectiveness. Validation experiments demonstrated that IoA-SoftNMS significantly increased detection accuracy, improving mean average precision (mAP) by 0.7 % to 3.5 % across various object detection models, without necessitating model retraining. Importantly, these enhancements barely affect the detection time. IoA-SoftNMS exhibited robust adaptability in detecting large images, especially when integrated with the slicing-aided hyper inference (SAHI) technique, where it notably improved detection accuracy during the slicing process. Application of IoA-SoftNMS elevates detection accuracy in medium (1000 × 3300 pixels) and large (2500 × 3400 pixels) images from 93 % to 96.9 % and 90.8 % to 95.3 %, respectively. These findings underscored the effectiveness of the proposed IoA-SoftNMS algorithm in improving object detection accuracy in agricultural settings and its potential to alleviate challenges posed by large image sizes, offering avenues for enhancing agricultural production precision and intelligence.