EllipseIoU: A General Metric for Aerial Object Detection

Successful management of the radio spectrum requires, as a first step, detailed information about spectrum occupancy. In this work, we present an end-to-end deep learning (DL) based framework to obtain information from wide spectrum bands through signal detection, localization, and modulation classification. By visually representing the radio signals in spectrograms, we formulate the wideband detection problem as an object detection task from the computer vision field. To this end, the proposed framework consists of two cascaded modules: an object detection network repurposed to detect and classify distinctive signals in wideband spectrograms, and a convolutional neural network (CNN) designed to extend the classification capabilities to support a wide range of analog and digital modulation schemes. To evaluate our framework, we use a public wideband recognition dataset, which we carefully analyze and curate through a series of preprocessing techniques. To tackle the challenges of insufficient training data and class imbalance observed in the dataset, we suggest a training strategy that includes data mixing and transfer learning. Our experimental results on a general test set demonstrate that the proposed approach can detect and classify a variety of narrowband signals with simultaneously high precision (77.1%), recall (81.8%), and localization accuracy, as indicated by an average Intersection over Union (IoU) of 86%.

Intersection over Union (IoU) is the most popular evaluation metric used in the object detection benchmarks. However, there is a gap between optimizing the commonly used distance losses for regressing the parameters of a bounding box and maximizing this metric value. The optimal objective for a metric is the metric itself. In the case of axis-aligned 2D bounding boxes, it can be shown that $IoU$ can be directly used as a regression loss. However, $IoU$ has a plateau making it infeasible to optimize in the case of non-overlapping bounding boxes. In this paper, we address the weaknesses of $IoU$ by introducing a generalized version as both a new loss and a new metric. By incorporating this generalized $IoU$ ($GIoU$) as a loss into the state-of-the art object detection frameworks, we show a consistent improvement on their performance using both the standard, $IoU$ based, and new, $GIoU$ based, performance measures on popular object detection benchmarks such as PASCAL VOC and MS COCO.

Latest advances in artificial intelligence, particularly in object recognition and segmentation, provide unprecedented opportunities for precision agriculture. This work investigates the use of state-of-the-art AI models, namely Meta’s Segment Anything (SAM) and GroundingDino, for the task of grape cluster detection in vineyards. Three different methods aimed at enhancing the instance segmentation process are proposed: (i) SAM-Refine (SAM-R), which refines a previously proposed depth-based clustering approach, referred to as DepthSeg, using SAM; (ii) SAM-Segmentation (SAM-S), which integrates SAM with a pre-trained semantic segmentation model to improve cluster separation; and (iii) AutoSAM-Dino (ASD), which eliminates the need for manual labeling and transfer learning through the combined use of GroundingDino and SAM. Analysis is conducted on both the object counting and pixel-level segmentation accuracy against a manually labeled ground truth. Metrics such as mean Average Precision (mAP), Intersection over Union (IoU), and precision and recall are calculated to assess the system performance. Compared to the original DepthSeg algorithm, SAM-R slightly advances object counting (mAP: +0.5%) and excels in pixel-level segmentation (IoU: +17.0%). SAM-S, despite a mAP decrease, improves segmentation accuracy (IoU: +13.9%, Precision: +9.2%, Recall: +11.7%). Similarly, ASD, although with a lower mAP, shows significant accuracy enhancement (IoU: +7.8%, Precision: +4.2%, Recall: +4.9%). Additionally, from a labor effort point of view, instance segmentation techniques require much less time for training than manual labeling.

Due to the complexity, diversity, or even small size of train bottom parts, the current object detection algorithm cannot identify it accurately. We propose a new method to solve the above problem. This method changes the computational way of loss based on Darknet-yolov3 for specific train bottom parts and improves the situation that the object detection network has low accuracy in detecting. IoU(Intersection over Union) can be directly used as a regression loss. However, IoU has a plateau making it infeasible to optimize in the case of nonoverlapping bounding boxes. We put forward XIoU to calculate the loss function. XIoU calculates the case when IoU is equal to zero and increases the amount of prediction sample for regression loss. The test set used the No.2 camera pictures provided by railway administration. Compared with Mobile-Net, Yolov3 and Yolov3-giou, the experimental results showed that the training results of XIoU were 10% higher than Mobile-Net and Yolov3 on mAP, and 0.2% higher than Yolov3-giou.

The main aim of optical remote sensing image (ORSI) object detection is to ascertain the area as well as class of all targets in given images. Nowadays, object detection methods established from deep learning are progressively applied to the analysis of the information from ORSI. But because of the compound background as well as extensive object scale shown in ORSI, the difficulty of object detection has increased. There are still some challenges to be solved. First, when the two bounding boxes don't overlap, current indexes like intersection over union (IoU) cannot identify the distance between them. Secondly, the existing methods using convolutional neural network (CNN) could not take advantage of the characteristics of multi-level features so that these methods are not very good at recognizing small-sized objects. To deal with these above problems, this paper comes up with a ORSI object detection method established on multi-level feature fusion as well as improved boundary box regression compared to IoU. Firstly, a new measure called generalized intersection over union (GIoU) is practiced. That metric could measure the similarity betwixt two bounding boxes, regardless of whether they overlap or not. At the same time, we also directly use GIoU as loss. Lastly, a multi-level feature fusion structure is practiced and it is also integrated into the existing convolutional neural network. In this way, our method could take advantage of the multi-level features. Quantitative comparison of the addressed method with the baseline approach on large-scale dataset named Dior are conducted. The comparison with the most advanced method shows that our method has reached the most advanced performance.

Intersection over Union (IoU) is an important function in object detection based on deep learning. But, there is a gap between the used distance losses and this metric value of maximizing. This paper improves the IoU function based on IoU. Redesigned the neural network structure, and used the PASCAL VOC2012 dataset. The structure model of the neural network is compare with others in the accuracy of object detection. Experimental results show that our method can achieve good results in object detection. The approach provides a new idea for object detection.

Object detection remains a cornerstone task in computer vision, with wide-ranging applications in autonomous driving, surveillance, and medical imaging. However, traditional methods rely heavily on large annotated datasets, limiting their adaptability in low-resource environments. We propose Hybrid Masked Autoencoder-Detection Transformer++ (HybridMAE-DETR++), a novel self-supervised object detection framework that synergizes Masked Autoencoders (MAEs) and DINOv2 for Vision Transformer (ViT) pretraining. Integrated with a Swin-ViT hybrid backbone and an enhanced DETR++ detection head, the framework significantly reduces dependence on annotated data while improving detection accuracy for small and occluded objects. Evaluated on COCO 2017 and Cityscapes, HybridMAE-DETR++ achieves 47.5% mean Average Precision (mAP) and 68.0% Intersection over Union (IoU) on COCO, and 53.2% mAP and 72.1% IoU on Cityscapes, outperforming DETR and other transformer-based baselines. Ablation and sensitivity analyses confirm the robustness of our hybrid pretraining strategy, and visualizations using Layer-weighted Class Activation Mapping (LayerCAM) and Gradient-weighted Class Activation Mapping++ (Grad-CAM++) validate model interpretability. Despite a moderate increase in training time, the precision gains justify the computational cost. This framework sets a new benchmark for label-efficient, interpretable object detection in real-world scenarios.

In recent years, deep learning based methods have achieved excellent performance in standard object detection. However, these methods lack sufficient capabilities to handle underwater object detection due to these challenges: (1) underwater images have color shift and low contrast, and (2) various noises (sediments, bubbles, etc.) would cause blurring in underwater images. To address these problems, our work investigates optimization policies to detect low-contrast and blurred mine. We propose a bounding box repairing algorithm based on Intersection over Union (IoU) optimization. The algorithm mainly optimizes Mask Scoring R-CNN network. Firstly, we use the Mask Scoring R-CNN model to generate the coarse-grained detection results of mines. Secondly, we perform IoU between the coarse-grained boxes and the annotated boxes in the dataset to obtain the best matching area. Finally, we use the best matching area to repair the coarse-grained boxes. Experimental results show that our method achieves promising object detection and localization performance in underwater environment.

Object detection is a challenging task in the field of remote sensing applications due to the complex backgrounds and uncertain orientation of targets. Compared with the horizontal bounding box, the oriented bounding box can provide orientation information while retaining the true size. Most existing oriented object detection methods are based on Faster-RCNN and the other one-stage methods that can achieve real-time speed but have shortcomings in localization and detection accuracy. To further enhance the performance of one-stage methods, we propose an oriented object detection framework that is based on the single shot detector, namely, single shot anchor refinement network (S²ARN). The S²ARN obtains the accurate detection results by performing two consecutive regressions. More precisely, the multilevel features of the backbone are used to regress the coordinate offsets between the predefined rotated anchors and the ground-truth boxes to generate the refined anchors. The classification and regression subnetworks assigned to the output features are used to perform the second regression to determine the class labels and further adjust the location of the refined anchors. In addition, receptive field amplification modules (RFAMs) are inserted to enlarge the receptive field and extract more discriminative features. Furthermore, in the anchor matching step, angle-related Intersection over Union (ArIoU) is used to calculate the Intersection over Union (IoU) score instead of the traditional method. Benefiting from the multiple regressions and the insensitivity of the ArIoU score to the angle deviation, the angle sampling interval of the rotated anchor can be reduced. The experimental results for the two public datasets, HRSC2016 and UCAS-AOD, demonstrate the effectiveness of the proposed network.

Accurate and robust object detection is of critical importance in airport surface surveillance to ensure the security of air transportation systems. Owing to the constraints imposed by a relatively fixed receptive field, existing airport surface detection methods have not yet achieved substantial advancements in accuracy. Furthermore, these methods are vulnerable to adversarial attacks with carefully crafted adversarial inputs. To address these challenges, we propose the Vision GNN-Edge (ViGE) block, an enhanced block derived from the Vision GNN (ViG). ViGE introduces the receptive field in pixel space and represents the spatial relation between pixels directly. Moreover, we implement an adversarial training strategy with augmented training samples generated by adversarial perturbation. Empirical evaluations on the public remote sensing dataset LEVIR and a manually collected airport surface dataset show that: 1. our proposed method surpasses the original model in precision and robustness; 2. defining the receptive field in pixel space performs better than that on representation space.

A method of real-time object detection using Radial Reach Correlation (RRC) has been developed. We also apply a statistical background estimation to cope with dynamic and complex environments. In order to reduce the computational cost of RRC for an embedded image processing device, we apply two techniques: fast RRC algorithm and background estimation based on statistical approach with cumulative averaging process. As a result, it is possible to reduce the RRC calculation process to about 1/4 in comparison with normal RRC. By combining these techniques, we can achieve robust real-time object detection.

In recent years, research on Unmanned Aerial Vehicles (UAVs) has developed rapidly. Compared to traditional remote-sensing images, UAV images exhibit complex backgrounds, high resolution, and large differences in object scales. Therefore, UAV object detection is an essential yet challenging task. This paper proposes a multi-scale object detection network, namely YOLO-DroneMS (You Only Look Once for Drone Multi-Scale Object), for UAV images. Targeting the pivotal connection between the backbone and neck, the Large Separable Kernel Attention (LSKA) mechanism is adopted with the Spatial Pyramid Pooling Factor (SPPF), where weighted processing of multi-scale feature maps is performed to focus more on features. And Attentional Scale Sequence Fusion DySample (ASF-DySample) is introduced to perform attention scale sequence fusion and dynamic upsampling to conserve resources. Then, the faster cross-stage partial network bottleneck with two convolutions (named C2f) in the backbone is optimized using the Inverted Residual Mobile Block and Dilated Reparam Block (iRMB-DRB), which balances the advantages of dynamic global modeling and static local information fusion. This optimization effectively increases the model’s receptive field, enhancing its capability for downstream tasks. By replacing the original CIoU with WIoUv3, the model prioritizes anchoring boxes of superior quality, dynamically adjusting weights to enhance detection performance for small objects. Experimental findings on the VisDrone2019 dataset demonstrate that at an Intersection over Union (IoU) of 0.5, YOLO-DroneMS achieves a 3.6% increase in mAP@50 compared to the YOLOv8n model. Moreover, YOLO-DroneMS exhibits improved detection speed, increasing the number of frames per second (FPS) from 78.7 to 83.3. The enhanced model supports diverse target scales and achieves high recognition rates, making it well-suited for drone-based object detection tasks, particularly in scenarios involving multiple object clusters.

Towards accurate dense pedestrian detection via occlusion-prediction aware label assignment and hierarchical-NMS

Software was developed in Python for the digital processing of object images before their detection using the You Only Look Once (YOLO) artificial neural network. Detection was carried out on object images, specifically vehicles and other road users. The preprocessing of images was performed through histogram equalization and local contrast enhancement. The original images were read from video cameras or graphic files. Image detection was performed using the medium-sized YOLO convolutional neural network model, YOLOv8m. As a result of detection, the studied objects, particularly cars, were highlighted with rectangular bounding boxes. To evaluate the accuracy of object detection, several metrics (parameters) were used: Precision, Recall, Intersection over Union (IoU), F1, and Average Precision (AP). The YOLO network was pre-trained on the Common Objects in Context dataset. The YOLO neural network returns the object recognition confidence, the coordinates of its center (x, y) on the image, and its width and height (w, h). The detected objects are marked with rectangular bounding boxes. The positioning of objects in the images was manually performed using the Roboflow tool, which allows for accurate spatial positioning of each object. The study of the impact of image preprocessing on the accuracy of object detection by the YOLO network was conducted using a typical traffic scene image. After histogram equalization, the histogram becomes more symmetrical and uniform, improving the visual quality of both dark and bright areas. This led to improved object detection accuracy across almost all metrics. The increase in detection accuracy by the IoU parameter is 0.169. The summary improvement in detection accuracy by the IoU, F1, AP parameters is 0.502. It was shown that after image preprocessing, detection accuracy increased, and all vehicles were correctly detected. The developed software can be used in various computer vision systems as well as in Internet of Things systems for remote monitoring and control.

Lesion segmentation in dermoscopic images significantly enhances the diagnostic performance of AI-based classification models. However, conventional methods often require pixel-level annotations, which are resource-intensive and prone to errors caused by external artifacts, such as hair and skin markings. We propose a hybrid framework called SAM-enhanced YOLO, which integrates the Segment Anything Model (SAM) with You Only Look Once (YOLO) for precise pixel-level segmentation. This method combines YOLO's efficient lesion localization with SAM's advanced zero-shot segmentation capabilities. To further validate the framework, we compared it against traditional methods, including GrabCut and Otsu's thresholding, as well as SAM used without YOLO (SAM-only). For SAM-only, lesion segmentation was initialized at the image center to simulate a typical dermoscopic imaging setup. SAM-enhanced YOLO demonstrated superior segmentation performance, achieving an Intersection over Union (IoU) of 0.738 and an F1-score (the harmonic mean of precision and recall) of 0.833, compared to 0.578 and 0.683 with SAM-only, respectively. This represents a 28% improvement in IoU and a 22% improvement in F1-score compared to SAM-only. The results were consistent across lesion shapes and contrast conditions, with SAM-enhanced YOLO exhibiting the lowest variability and highest robustness among the evaluated methods. By reducing the need for pixel-level annotations and outperforming both standalone SAM and traditional methods, SAM-enhanced YOLO provides a scalable and resource-efficient solution for dermoscopic lesion segmentation. This framework holds significant potential for improving diagnostic workflows in clinical and resource-limited settings.