Aerial Small Object Tracking with Transformers

A Real-World Size Organization of Object Responses in Occipitotemporal Cortex

Object detection and tracking are vital in computer vision and visual surveillance, allowing for the detection, recognition, and subsequent tracking of objects within images or video sequences. These tasks underpin surveillance systems, facilitating automatic video annotation, identification of significant events, and detection of abnormal activities. However, detecting and tracking small objects introduce significant challenges within computer vision due to their subtle appearance and limited distinguishing features, which results in a scarcity of crucial information. This deficit complicates the tracking process, often leading to diminished efficiency and accuracy. To shed light on the intricacies of small object detection and tracking, we undertook a comprehensive review of the existing methods in this area, categorizing them from various perspectives. We also presented an overview of available datasets specifically curated for small object detection and tracking, aiming to inform and benefit future research in this domain. We further delineated the most widely used evaluation metrics for assessing the performance of small object detection and tracking techniques. Finally, we examined the present challenges within this field and discussed prospective future trends. By tackling these issues and leveraging upcoming trends, we aim to push forward the boundaries in small object detection and tracking, thereby augmenting the functionality of surveillance systems and broadening their real-world applicability.

Minimal and maximal distances of radar visibility and tracking of small objects were measured in different weather conditions in the Gulf of Gda?sk and at high sea on big tanker ship and s/v Dar M?odzie?y. Radars working in S and X band were used. Different small objects, including buoys, hydrofoil boats and high-speed crafts, were observed and tracked on different radars in different weather conditions. Results of these experiments will be presented in this paper.

本文设计了一款应用于UHF频段的RFID近场环形标签天线。该天线通过相邻弯折导线间的反向电流削弱环形结构带来的强感抗，有利于实现阻抗匹配和提升带宽；利用向内弯折结构有效的缩减了天线尺寸，可应用于小尺寸物体追踪识别。最终天线印制在FR-4介质板上，尺寸为7.9 × 10.2 × 0.2 mm3，相比同类型天线缩减了42.1%。仿真与测试结果表明天线在近场区域有很好的性能，可应用在UHF RFID系统。 A near-field loop tag antenna for UHF RFID system is proposed. By reverse current from bending adjacent wires to weaken the strong inductive from loop antenna, it’s good for impedance matching and bandwidth promoting; the antenna size can be reduced effectively by the inward bent structure, which can be applied to the small size object tracking identification. The antenna is printed onto the FR-4 substrate, with an overall size of 7.9 × 10.2 × 0.2 mm3, compared to the same type, size of the antenna is reduced to 42.1%. The simulation and test results show that the antenna has a good performance in the near-field region, which can be used in UHF RFID systems.

With the increasing popularity of Unmanned Aerial Vehicles (UAVs), the accuracy of detecting small objects in large-view images is also expected to increase. However, accurate small object detection is still a challenging problem. Currently, Image Pyramid Network, Feature Pyramid Network (FPN), rich training strategies and data augmentation are widely used to address this problem. To accurately detect small objects, the most important thing is to mine for more feature information. We propose Widened Residual Block (WRB) to break through the bottleneck of residual information gain to extract more feature information. The second is to emphasize or suppress features to prevent small objects from being overwhelmed by a broad background. We introduce an attention mechanism into PANet and propose Enhanced Attention PANet (EA-PANet), which consists of two parts: Context Attention Module (COAM) and Attention Enhancement Module (AEM). COAM outputs attention heatmaps with context, and AEM fuses features from the channel attention module (CAM) and COAM to avoid distraction from a vast background. In addition, we design a lightweight Decoupled Attention Head (DA-head) to dynamically compute important regions for specific tasks and achieve reliable predictions. Experiments show that our method outperforms state-of-the-art (SOTA) detectors. The source code for this work is available at https://github.com/liuxiaolei111/FindSmallObjects.

Learning-based infrared small object detection methods currently rely heavily on the classification backbone network. This tends to result in tiny object loss and feature distinguishability limitations as the network depth increases. Furthermore, small objects in infrared images are frequently emerged bright and dark, posing severe demands for obtaining precise object contrast information. For this reason, we in this paper propose a simple and effective "U-Net in U-Net" framework, UIU-Net for short, and detect small objects in infrared images. As the name suggests, UIU-Net embeds a tiny U-Net into a larger U-Net backbone, enabling the multi-level and multi-scale representation learning of objects. Moreover, UIU-Net can be trained from scratch, and the learned features can enhance global and local contrast information effectively. More specifically, the UIU-Net model is divided into two modules: the resolution-maintenance deep supervision (RM-DS) module and the interactive-cross attention (IC-A) module. RM-DS integrates Residual U-blocks into a deep supervision network to generate deep multi-scale resolution-maintenance features while learning global context information. Further, IC-A encodes the local context information between the low-level details and high-level semantic features. Extensive experiments conducted on two infrared single-frame image datasets, i.e., SIRST and Synthetic datasets, show the effectiveness and superiority of the proposed UIU-Net in comparison with several state-of-the-art infrared small object detection methods. The proposed UIU-Net also produces powerful generalization performance for video sequence infrared small object datasets, e.g., ATR ground/air video sequence dataset. The codes of this work are available openly at https://github.com/danfenghong/IEEE_TIP_UIU-Net.

In this paper we consider the tracking of small distant objects using Radar and Electro-Optical (EO) sensors. In particular we address the problem of data association after coalescence - this happens when two objects become sufficiently close (in angular terms) that they can no longer be resolved by the EO sensor. Some moments later they de-coalesce and the resulting detections must be associated with the existing tracks in the EO sensor. Traditionally this would be solved by making use of the velocity vectors of the objects prior to coalescence. This approach can work well for crossing objects, but when the objects are largely moving in a direction radial to the sensor it becomes problematic. Here we investigate the use of data fusion to combine Radar range with a brightness measure derived from an EO sensor to enhance the accuracy of data association. We present a number of results on the performance of this approach taking into account target motion, atmospheric conditions and sensor noise.

In recent years, detection methods for generic object detection have achieved significant progress. However, due to the large number of small objects in aerial images, mainstream detectors struggle to achieve a satisfactory detection performance. The challenges of small object detection in aerial images are primarily twofold: (1) Insufficient feature representation: The limited visual information for small objects makes it difficult for models to learn discriminative feature representations. (2) Background confusion: Abundant background information introduces more noise and interference, causing the features of small objects to easily be confused with the background. To address these issues, we propose a Multi-Level Contextual and Semantic Information Aggregation Network (MCSA-Net). MCSA-Net includes three key components: a Spatial-Aware Feature Selection Module (SAFM), a Multi-Level Joint Feature Pyramid Network (MJFPN), and an Attention-Enhanced Head (AEHead). The SAFM employs a sequence of dilated convolutions to extract multi-scale local context features and combines a spatial selection mechanism to adaptively merge these features, thereby obtaining the critical local context required for the objects, which enriches the feature representation of small objects. The MJFPN introduces multi-level connections and weighted fusion to fully leverage the spatial detail features of small objects in feature fusion and enhances the fused features further through a feature aggregation network. Finally, the AEHead is constructed by incorporating a sparse attention mechanism into the detection head. The sparse attention mechanism efficiently models long-range dependencies by computing the attention between the most relevant regions in the image while suppressing background interference, thereby enhancing the model’s ability to perceive targets and effectively improving the detection performance. Extensive experiments on four datasets, VisDrone, UAVDT, MS COCO, and DOTA, demonstrate that the proposed MCSA-Net achieves an excellent detection performance, particularly in small object detection, surpassing several state-of-the-art methods.

Compared with conventional targets, small objects often face challenges such as smaller size, lower resolution, weaker contrast, and more background interference, making their detection more difficult. To address this issue, this paper proposes an improved small object detection method based on the YOLO11 model-PC-YOLO11s. The core innovation of PC-YOLO11s lies in the optimization of the detection network structure, which includes the following aspects: Firstly, PC-YOLO11s has adjusted the hierarchical structure of the detection network and added a P2 layer specifically for small object detection. By extracting the feature information of small objects in the high-resolution stage of the image, the P2 layer helps the network better capture small objects. At the same time, in order to reduce unnecessary calculations and lower the complexity of the model, we removed the P5 layer. In addition, we have introduced the coordinate spatial attention mechanism, which can help the network more accurately obtain the spatial and positional features required for small targets, thereby further improving detection accuracy. In the VisDrone2019 datasets, experimental results show that PC-YOLO11s outperforms other existing YOLO-series models in overall performance. Compared with the baseline YOLO11s model, PC-YOLO11s mAP@0.5 increased from 39.5% to 43.8%, mAP@0.5:0.95 increased from 23.6% to 26.3%, and the parameter count decreased from 9.416M to 7.103M. Not only that, we also applied PC-YOLO11s to tea bud datasets, and experiments showed that its performance is superior to other YOLO-series models. Experiments have shown that PC-YOLO11s exhibits excellent performance in small object detection tasks, with strong accuracy improvement and good generalization ability, which can meet the needs of small object detection in practical applications.

Since small objects occupy less pixels in the image and are difficult to recognize. Small object detection has always been a research difficulty in the field of computer vision. Aiming at the problems of low sensitivity and poor detection performance of YOLOv3 for small objects. AFYOLO, which is more sensitive to small objects detection was proposed in this paper. Firstly, the DenseNet module is introduced into the low-level layers of backbone to enhance the transmission ability of objects information. At the same time, a new mechanism combining channel attention and spatial attention is introduced to improve the feature extraction ability of the backbone. Secondly, a new feature pyramid network (FPN) is proposed to better obtain the features of small objects. Finally, ablation studies on ImageNet classification task and MS-COCO object detection task verify the effectiveness of the proposed attention module and FPN. The results on Wider Face datasets show that the AP of the proposed method is 11.89%higher than that of YOLOv3 and 8.59%higher than that of YOLOv4. All of results show that AFYOLO has better ability for small object detection.

Detecting dense, small litter on water surfaces presents a significant challenge in the field of unmanned litter-cleaning vehicles. Dense small objects on water surfaces are easily influenced by various factors, including ripples, reflections, and changing lighting conditions. Existing detection methods often fail to effectively mine multidimensional global features and tend to overlook the impact of feature conflicts on small object detection. To overcome these challenges, we propose the Dense Small Floating Litter Detection Network (DSFLDNet), which incorporates multidimensional attention mechanisms in both the spatial and frequency domains. We have designed spatial and channel attention modules that utilize multiple sets of orthogonal frequency filters to enhance the network's sensitivity to small objects against complex water surface backgrounds. In our backbone architecture, we enhance feature extraction capabilities through parallel information extraction and channel blending techniques. A feature fusion approach that combines a feature pyramid with multidimensional attention mechanisms is implemented to mitigate conflicts between features at different levels, thereby improving overall detection accuracy. The proposed model demonstrates optimal experimental performance on both custom private datasets and publicly available data. Specifically, it achieves an accuracy of 93.1%, a recall rate of 93.9%, and a mean average precision of 97.3% on the Dense Small Object Datasets, with a processing frame rate of 107 frames per second. Moreover, this model has been successfully deployed on an unmanned vessel for real-time detection, proving to be an effective tool for cleaning and recycling debris from water surfaces.

Infrared video small object detection is pivotal in numerous security and surveillance applications. However, existing deep learning-based methods, which typically rely on a two-step paradigm of frame-by-frame detection followed by temporal refinement, struggle to effectively utilize temporal information. This is particularly challenging when detecting small objects against complex backgrounds. To address these issues, we introduce the One-Step Transformer (OSFormer), a novel method that pioneeringly integrates a small-object-friendly transformer with a one-step detection paradigm. Unlike traditional methods, OSFormer processes the video sequence only through a single inference, encoding the sequence into cube format data and tracking object motion trajectories. Additionally, we propose the Varied-Size Patch Attention (VPA) module, which generates patches of varying sizes to capture adaptive attention features, bridging the gap between transformer architectures and small object detection. To further enhance detection accuracy, OSFormer incorporates a Doppler Adaptive Filter, which integrates traditional filtering techniques into an end-to-end neural network to suppress background noise and accentuate small objects. OSFormer outperforms YOLOv8-s on both the AntiUAV dataset (+ $3.1\%~\text {mAP}_{50}$ , - $35.1\%~\text {Params}$ ) and the InfraredUAV dataset (+ $4.0\%~\text {mAP}_{50-95}$ , - $51.0\%~\text {FLOPs}$ ), demonstrating superior efficiency and effectiveness in small object detection. The code is available on https://github.com/q2479036243/OSFormer.

Accurate identification of small tea buds is a key technology for tea harvesting robots, which directly affects tea quality and yield. However, due to the complexity of the tea plantation environment and the diversity of tea buds, accurate identification remains an enormous challenge. Current methods based on traditional image processing and machine learning fail to effectively extract subtle features and morphology of small tea buds, resulting in low accuracy and robustness. To achieve accurate identification, this paper proposes a small object detection algorithm called STF-YOLO (Small Target Detection with Swin Transformer and Focused YOLO), which integrates the Swin Transformer module and the YOLOv8 network to improve the detection ability of small objects. The Swin Transformer module extracts visual features based on a self-attention mechanism, which captures global and local context information of small objects to enhance feature representation. The YOLOv8 network is an object detector based on deep convolutional neural networks, offering high speed and precision. Based on the YOLOv8 network, modules including Focus and Depthwise Convolution are introduced to reduce computation and parameters, increase receptive field and feature channels, and improve feature fusion and transmission. Additionally, the Wise Intersection over Union loss is utilized to optimize the network. Experiments conducted on a self-created dataset of tea buds demonstrate that the STF-YOLO model achieves outstanding results, with an accuracy of 91.5% and a mean Average Precision of 89.4%. These results are significantly better than other detectors. Results show that, compared to mainstream algorithms (YOLOv8, YOLOv7, YOLOv5, and YOLOx), the model improves accuracy and F1 score by 5-20.22 percentage points and 0.03-0.13, respectively, proving its effectiveness in enhancing small object detection performance. This research provides technical means for the accurate identification of small tea buds in complex environments and offers insights into small object detection. Future research can further optimize model structures and parameters for more scenarios and tasks, as well as explore data augmentation and model fusion methods to improve generalization ability and robustness.

Video object detection is essential for airport surface surveillance, but the objects on the scene are mostly small objects with low resolution, they have no obvious feature information. Due to the scale differences of the objects and the fixed receptive field on the feature maps, detectors cannot model multi‐scale context information and cover all objects. In addition, although the video detection algorithm can be used as a method to solve the problem of small object detection, the temporal feature fusion method of current video detection is very dependent on the quality of a single feature map. Therefore, this paper aims to enhance the features of small objects of a single image. First, an attentional multi‐scale feature fusion enhancement (A‐MSFFE) network is built on the memory‐enhanced global‐local aggregation (MEGA) to supplement semantic and spatial information of small objects. Then, a context feature enhancement (CFE) module is designed for obtaining different receptive fields through different dilated convolutions. Meanwhile, a video detection dataset about the airport is established. Finally, the experimental results show that the proposed method can improve the detection accuracies of small objects and outperform other state‐of‐the‐art video object detection algorithms in self‐built airport dataset.

A literature analysis has shown that object search, recognition, and tracking systems are becoming increasingly popular. However, such systems do not achieve high practical results in analyzing small moving living objects ranging from 8 to 14 mm. This article examines methods and tools for recognizing and tracking the class of small moving objects, such as ants. To fulfill those aims, a customized You Only Look Once Ants Recognition (YOLO_AR) Convolutional Neural Network (CNN) has been trained to recognize Messor Structor ants in the laboratory using the LabelImg object marker tool. The proposed model is an extension of the You Only Look Once v4 (Yolov4) 512 × 512 model with an additional Self Regularized Non–Monotonic (Mish) activation function. Additionally, the scalable solution for continuous object recognizing and tracking was implemented. This solution is based on the OpenDatacam system, with extended Object Tracking modules that allow for tracking and counting objects that have crossed the custom boundary line. During the study, the methods of the alignment algorithm for finding the trajectory of moving objects were modified. I discovered that the Hungarian algorithm showed better results in tracking small objects than the K–D dimensional tree (k-d tree) matching algorithm used in OpenDataCam. Remarkably, such an algorithm showed better results with the implemented YOLO_AR model due to the lack of False Positives (FP). Therefore, I provided a new tracker module with a Hungarian matching algorithm verified on the Multiple Object Tracking (MOT) benchmark. Furthermore, additional customization parameters for object recognition and tracking results parsing and filtering were added, like boundary angle threshold (BAT) and past frames trajectory prediction (PFTP). Experimental tests confirmed the results of the study on a mobile device. During the experiment, parameters such as the quality of recognition and tracking of moving objects, the PFTP and BAT, and the configuration parameters of the neural network and boundary line model were analyzed. The results showed an increased tracking accuracy with the proposed methods by 50%. The study results confirmed the relevance of the topic and the effectiveness of the implemented methods and tools.