Moving object detection via TV-L1 optical flow in fall-down videos

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.

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.

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

Recently, object detection has gained significant progress in remote sensing images. Nevertheless, we conclude two defects in remote sensing image object detection. At first, most methods rely on feature pyramid, but the features of different levels would influence each other when we use top-down operation. Second, the traditional label assignment strategy cannot assign suitable labels, as it adopts the fixed intersection over union (IoU) threshold to divide positive samples and negative samples during training. According to the problems we pointed out, a simple yet effective framework is employed to eliminate these two limitations. It integrates two novel components: aware feature pyramid network (AFPN) and group assignment strategy (GAS). AFPN is to mitigate the adverse effects caused by the first problem. Specifically, it learns a vector for the higher level features in the feature pyramid to obtain clean features. As for the second limitation, we recommend a new label assignment strategy named GAS to address this problem. Samples will be grouped according to their overlaps with ground truth, and then, they are assigned to positive or negative labels in each group. Extensive experiments are conducted on the large-scale object detection dataset DIOR and DOTA. With the newly introduced two key components, our model significantly improves the detection accuracy. Without bells and whistles, our proposed method achieves 2.0% and 1.9% higher mean average precision (mAP) than Faster R-CNN with FPN when using ResNet50 and ResNet101 as the backbones, respectively. Finally, we obtain 73.3% mAP on the DIOR dataset without any tricks. Our code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/hm-better/dior_detect</uri> .

Recent studies on Parkinson's Disease (PD) discovered potential markers in brain MR images for its diagnosis and staging.One of them is the neuromelanin, which can be found in regions such as the substantia nigra and the locus coeruleus, both located in the brainstem.The analysis of these regions is normally conducted manually by a specialized professional, which can be costly and timeconsuming.Fortunately, there have been advances in automatic segmentation approaches in several areas.In medical imaging, U-Nets are showing state-of-the-art performance, but we did not find many works using this architecture to extract brainstem structures.A likely cause for this is the scarcity of large databases with well annotated segmentation of these areas.Thus, this paper explores the use of a dataset of our research group composed of T1-weighted MR images to train U-Net models with different types of slices to automatically demarcate the brainstem (as a first stage).The analysis starts with a scripted segmentation of the target region using the Freesurfer package.Thereby, we trained 4 models and evaluated them using Dice Similarity Coefficient (DSC) and Intersection over Union (IoU).Three models were trained on single anatomical planes, and one on multi-plane slices.Also, we applied grid search, varying optimizers, numbers of filters in the first layer, and learning rates.The best model trained with the larger subset with the best performance was the axial (DSC: 91.76% and IoU: 86.95%), followed by sagittal (DSC: 90.61% and IoU: 84.11%), coronal (DSC: 89.38% and IoU: 68.76%), and all slices (DSC: 16.36% and IoU: 7.58%).The next steps of our research are to differentiate the midbrain out of the brainstem, considering manual segmentation as ground truth, and test some approaches on determining the threshold and evaluating separately the 2 hemispheres of the midbrain.

Object detection is a fundamental task in computer vision. Bounding box regression (BBR) losses are critical to detector performance. However, evaluation measures that rely on the Intersection over Union (IoU) between the predicted and ground truth boxes are highly sensitive to positional deviations, which can hinder optimization. To alleviate this issue, we propose ATDIoU, a novel arctangent-differential loss for bounding-box regression. ATDIoU computes distance similarity between a predicted and a ground truth box by modeling the distances between their corresponding vertices as a two-dimensional arctangent differential distribution (ATD). This arctangent differential-based design mitigates bounding box drift and reduces sensitivity to localization errors. As a result, it guides the model to learn target positions more effectively. We evaluate ATDIoU by integrating it into YOLOv6 and conducting experiments on PASCAL VOC and VisDrone2019. The results demonstrate that ATDIoU yields improvements of 1.4% and 0.7% in mean average precision (mAP) relative to MPDIoU.

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.

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.

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.

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.

Existing works in object detection usually adopt different Intersection over Union (IoU) metrics to define the similarity between predicted box and target box, which greatly boost the detection performance. For the task of aerial object detection, since the predicted and target boxes are with different sizes, aspect ratios and orientations, existing IoU metrics can not measure their similarity well. In this work, we propose a new and generic metric for robust aerial object detection, called EllipseIoU, which incorporates the ellipse distance between the predicted box and the target box. In particular, we find the inner ellipse from the box, and then calculate the ellipse distance between predicted and target boxes based on the distances of focal points. We prove that the proposed ellipse distance well measures the relations of sizes, aspect ratios and orientations between predicted and target boxes. Moreover, we also incorporate the relation of short axis length between two boxes to measure the relation of sizes. Based on the ellipse distance, we design the EllipseIoU metric by combining with the IoU metric and integrate it into detectors for performance boosting of aerial object detection. Experimental results on public datasets show that the detector with EllipseIoU significantly improve the baseline without impact on the efficiency and achieves state-of-the-art performance.KeywordsAerial object detectionIntersection over Union (IoU)

YOLO-YCbCr based smoke segmentation method for fire detection was proposed in this study to enhance smoke segmentation performance with reduction in computational cost. The proposed method consists of the deep learning object detection model, You Only Look Once (YOLO), and the color space-based segmentation model, rule-based YCbCr. YOLO is used to detect smoke objects in the input fire images through bounding boxes. The images in the bounding boxes are characterized based on YCbCr color space and the proposed YCbCr rules derived by considering smoke image characteristics segment smoke region. In order to evaluate the smoke segmentation performance, six different fire incident video data were used. The mean intersection over union (IoU) value of the proposed method was improved by approximately 31.3% and 24.5% respectively when compared to the reference models: YOLO-RGB model and YOLO-CIELAB model. It was found that YOLO significantly reduced the erroneous smoke segmentation and YCbCr rules derived from the smoke color features were effective in the smoke segmentation.

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.

Automatic spondylolisthesis grading from MRIs across modalities using faster adversarial recognition network.