A YOLO-Based Method for Head Detection in Complex Scenes.

Camouflaged object detection (COD) aims to accurately detect objects that blend in with their backgrounds. While deep learning-based methods have significantly improved detection accuracy, the persistent similarity in chromatic and textural characteristics between camouflaged objects and their environments continues to pose substantial challenges, particularly in complex scenarios. Existing COD methods still encounter two primary challenges: (1) the difficulty in effectively fusing detailed features with semantic representations, leading to suboptimal balance between local and global features in the fused features; (2) progressive information dilution in conventional top-down decoder architectures, resulting in imprecise boundary localization. To address these dual challenges of multi-scale feature enhancement and semantic information dilution, we propose a D ual-Branch C ross-Layer I nformation F low Network (DCIFNet) for camouflaged object detection in complex scenes. Specifically, our framework integrates a hybrid CNN-ViT architecture for parallel extraction of localized patterns and global contextual features. Subsequently, a global local fusion (GLF) module is employed to iteratively and adaptively fuse the global and local features at each stage using gating weights. Additionally, a novel Dense Connection Decoder (DCD) module is designed to mitigate the information dilution problem associated with traditional top-down decoders. Extensive experiments show that DCIFNet outperforms other mainstream COD models in most performance metrics on four widely used benchmark datasets. On the COD10K dataset, compared with the latest SOTA work of PRNet, DCIFNet improves the metrics of \({S_{\alpha}}\) , \({E_{\phi}}\) , and \(F_{\beta}^{w}\) by 0.11 \(\%\) , 0.11 \(\%\) , and 1.38 \(\%\) , respectively, demonstrating a significant performance enhancement. The code is available https://github.com/WateverOk/DCIFNet .

Environmental protection is still a key issue that cannot be ignored at this stage of social development. With the development of artificial intelligence, various technologies increasingly tend to be widely used in the field of environmental protection, such as searching the wilderness through an unmanned aerial vehicle (UAV) and cleaning garbage by robots. Traditional object detection algorithms for this scenario suffer from low accuracy and high computational cost. Therefore, this paper proposes an algorithm applied to automatic garbage detection and instance segmentation in complex scenes. First, we construct sample-fused feature pyramid networks (SF-FPN) to achieve multi-scale feature sampling on multiple levels, to enhance the semantic representation of features. Second, adding the mask branch based on conditional convolution, introducing the idea of instance-filters to automatically generate the filter parameters of the Fully Convolutional Networks (FCN), to realize the instance-level pixel classification. Moreover, the Atrous Spatial Pyramid Pooling (ASPP) module is introduced to encode the feature information in a dense way to assist the generation of MASK. Finally, the object is detected and the instance is segmented by a two-branch structure. In addition, we also perform data augmentation on the original dataset to prevent model overfitting. The proposed algorithm reaches 82.7 and 72.4 according to the mAP index of detection and instance segmentation while using the public TACO dataset.

SummaryAs various algorithms and models spring up, object detection‐based deep learning for image analysis has become an established technology in the field of computer vision. Furthermore, object detection for high‐resolution videos derived from ubiquitous surveillance cameras draws many researchers' attention due to its practical significance and the challenge on detecting accuracy and speed. Existing object detection methods mainly resize and compress each frame in the video and then apply the detection algorithm, but with the method, the detection for small objects in dense scenes is far from satisfactory in terms of accuracy because small objects are reduced to pixel‐level sizes in compressed frame images. In order to fix this issue, we propose AROD, a parallel detection framework based on adaptive image cropping. Unlike the traditional first‐compression‐and‐then‐detection methods, AROD adopts adaptive image cropping for distributed parallel detection. In this way, AROD significantly improves the accuracy of small object detection in dense scenes with acceptable overhead. In our experimental evaluation, YOLOv2‐tiny model equipped with AROD reaches 29.29 FPS along with high detection accuracy. Experimental results verify that AROD ensures the high throughput of real‐time video analytics while maintaining high detection accuracy.

Salient object detection in complex scenes and environments is a challenging research topic. Most works focus on RGB-based salient object detection, which limits its performance of real-life applications when confronted with adverse conditions such as dark environments and complex backgrounds. Taking advantage of RGB and thermal infrared(RGBT) images becomes a new research direction for detecting salient objects in complex scenes, since the thermal infrared spectrum provides the complementary information and has been used in many computer vision tasks. However, current research for RGBT salient object detection is limited by the lack of a large-scale dataset and comprehensive benchmark. This work contributes such a RGBT image dataset named VT5000, including 5000 spatially aligned RGBT image pairs with ground truth annotations. VT5000 has 11 challenges collected in different scenes and environments for exploring the robustness of algorithms. With this dataset, we propose a powerful baseline approach, which extracts multilevel features of each modality and aggregates these features of all modalities with the attention mechanism for accurate RGBT salient object detection. To further solve the problem of blur boundaries of salient objects, we also use an edge loss to refine the boundaries. Extensive experiments show that the proposed baseline approach outperforms the state-of-the-art methods on VT5000 dataset and other two public datasets. In addition, we carry out a comprehensive analysis of different algorithms of RGBT salient object detection on VT5000 dataset, and then make several valuable conclusions and provide some potential research directions for RGBT salient object detection. Our new VT5000 dataset is made publicly available at https://github.com/lz118/RGBT-Salient-Object-Detection.

In recent years, computer vision technology has developed rapidly, as one of its important research directions, object detection has received widespread attention due to its high accuracy. Meanwhile, object detection has many application fields, such as intelligent transportation, medical and health, security systems, etc. Traditional object detection methods have limitations when applied to complex real-world scenarios. To improve the shortcomings of conventional methods, deep learning based object detection algorithms have significantly improved the efficiency of object detection and become a research hotspot in object detection. This article summarizes the algorithms into two-stage and one-stage object detection algorithms based on the technical processes and structural differences in handling object detection tasks. Firstly, several common two-stage and one-stage object detection algorithms and their applications in real-world scenarios are introduced. Then their data sets and algorithm performance are analyzed and compared. Finally, according to the results of the comparison, the existing problems of the two-stage object detection algorithm and the one-stage object detection method are discussed, and their future development directions are pointed out.

Detecting multiple salient objects in complex scenes is a challenging task. In this paper, we present a novel method to detect salient objects in images. The proposed method is based on the general ‘center-surround’ visual attention mechanism and the spatial frequency response of the human visual system (HVS). The saliency computation is performed in a statistical way. This method is modeled following three biologically inspired principles and compute saliency by two ‘scatter matrices’ which are used to measure the variability within and between two classes, i.e., the center and surrounding regions, respectively. In order to detect multiple salient objects of different sizes in a scene, the saliency of a pixel is estimated via its saliency support region which is defined as the most salient region centered at the pixel. Compliance with human perceptual characteristics enables the proposed method to detect salient objects in complex scenes and predict human fixations. Experimental results on three eye tracking datasets verify the effectiveness of the method and show that the proposed method outperforms the state-of-the-art methods on the visual saliency detection task.

Complexity of object movement and lack of object information due to occlusion have been the bottleneck which restricts the progress of object detection research. Whereas laser point cloud makes up the above deficiencies due to its 3D information. This paper analyzes the characteristics of laser data which is interpreted according to the data format and mathematical model of scanning equipment. Through extracting 3D object information and excavating object features of laser point cloud, various feature information of object is defined. Based on integrated learning method, train the object detector of laser point cloud and then achieve object detection in complex scenes. Experimental results show that object detection method based on 3D information extraction of laser point cloud improves the detection performance. Research results provide new research ideas and theoretical basis for the improvement of object detection performance.

ISA: Ingenious Siamese Attention for object detection algorithms towards complex scenes

With the rapid development of autonomous driving technology, traditional object detection algorithms often face challenges such as the trade-off between model parameters and recognition accuracy, insufficient detection accuracy, and slow detection speed when dealing with vehicle and pedestrian detection tasks in complex scenarios. To address these challenges, we propose a novel lightweight real-time driving scene detection network, FEEP-YOLO. Based on the YOLOv8 algorithm, our network not only maintains high detection accuracy but also achieves faster training speed and fewer model parameters. FEEP-YOLO employs a lightweight network, Faster Net, to significantly reduce model parameters, thereby accelerating detection speed and better meeting real-time requirements. To further improve detection accuracy, we introduce an EMA attention module into the network and optimize the bounding box loss function, adopting the EIOU loss function to enhance target features and reduce background interference. Additionally, to detect small objects more accurately, we add feature layers rich in semantic information to the detection end. Experimental results demonstrate that FEEP-YOLO outperforms YOLOv8 in terms of both detection speed and accuracy on the KITTI and SODA datasets, while significantly reducing the number of model parameters and model size. FEEP-YOLO achieves high detection speed while improving detection accuracy and reducing computational resource consumption, meeting the practical application requirements under limited computing power, memory space and power consumption. The key contribution of FEEP-YOLO lies in its ability to balance accuracy speed, and efficiency, making it a robust solution for real-time autonomous driving applications in complex environments.

Unmanned aerial vehicles (UAVs) have been widely used in post-disaster search and rescue operations, object tracking, and other tasks. Therefore, the autonomous perception of UAVs based on computer vision has become a research hotspot in recent years. However, UAV images include dense objects, small objects, and arbitrary object directions, which bring about significant challenges to existing object detection methods. To alleviate these issues, we propose a global-local feature enhanced network (GLF-Net). Considering the difficulty of processing UAV images with complex scenes and dense objects, we designed a backbone based on an involution and self-attention that can extract effective features from complex objects. A multiscale feature fusion module is also proposed to address the presence of numerous small objects in UAV images through multiscale object detection and feature fusion. To accurately detect rotated objects, a rotated regional proposal network was designed based on the midpoint offset representation, which can apply a rotated box to determine the real direction and contour of an object. GLF-Net achieves a state-of-the-art detection accuracy (86.52% mAP) on our created RO-UAV dataset, while achieving 96.95% and 97% mAP on the public datasets HRSC2016 and UCAS-AOU, respectively. The experimental results demonstrate that our method achieves a high detection accuracy and generalization, which can meet the practical requirements of UAVs under various complex scenarios.

Fire detection is critical to life. However, the reality of the scene is very complex. Interference from various scenarios makes it difficult to detect fires in a timely manner, e.g., there may be occluded fires in complex scenarios, which results in smaller flame targets that are difficult to detect and higher leakage and false detection rates. To address the above limitations, we develop a novel deep learning method, i.e., RCM, for complex scenarios. Specifically, it expands the model’s sensory field to capture the fire background information more extensively by designing a novel residual feature extraction network, i.e., RDNet, and combines it with the convolutional block attention module (CBAM) so that the model can pay more attention to the fire region, thus effectively reducing the interference of a complex background. Then, the multiscale feature fusion (MFF) module provides the model with a multilevel feature representation, which enhances the model’s ability to capture detailed features of smaller fires. Moreover, we introduce a new loss function, MPDIoU, to improve the convergence speed and detection accuracy of the model. Experiments on real fire scene datasets show that the precision and accuracy of the RCM model reach 94.77% and 97.99%, respectively, while the FPR and FNR are only 1.19% and 5.57%. Meanwhile, the detection performance of the method is optimized compared to more advanced algorithms in the field. The method demonstrates the effectiveness of fire detection in complex scenes and provides a novel and effective technique for fire detection.

Remote sensing change detection (RSCD) plays a crucial role in environmental monitoring, resource management, and land planning. However, remote sensing images typically involve multiple surface types, and the similarities and differences between these types make change detection in complex scenes even more challenging. Therefore, extracting and integrating effective features in complex scenes becomes a key issue in RSCD. In recent years, SAM2 and Mamba have made a significant impact in the field of computer vision, but further research is needed in the remote sensing domain to fully leverage their advantages. Thus, this paper proposes a two-stage change detection network named SAM-Mamba. Specifically, we use SAM2 as the encoder to extract key features from remote sensing images and perform preliminary decoding to generate mixed prompts, which are then passed to the guiding encoder (PE) to generate accurate and stable feature boundaries. These boundaries are then fused with the key features and passed to the decoder. In the decoding stage, we integrate the Mamba model, which is designed to efficiently model long sequences and capture spatiotemporal correlations. Furthermore, to enhance the ability to capture complex changes, we design the Frequency-guided Feature Refinement (FGFR) module and Dynamic Feature Fusion (DFM) module. Our SAM-Mamba outperforms other state-of-the-art methods on four datasets (e.g., Intersection over Union (IoU) and F1-score are improved by 3.40%/2.96%, 1.02%/1.07% and 2.52%/2.42% on LEVIR-CD+, WHU-CD and SYSU-CD datasets, respectively). The code of SAM-Mamba are publicly released at https://github.com/lytwxyyyds/Sam-Mamba.

In this paper, we investigate the detection of semantic human actions in complex scenes. Unlike conventional action recognition in well-controlled environments, action detection in complex scenes suffers from cluttered backgrounds, heavy crowds, occluded bodies, and spatial-temporal boundary ambiguities caused by imperfect human detection and tracking. Conventional algorithms are likely to fail with such spatial-temporal ambiguities. In this work, the candidate regions of an action are treated as a bag of instances. Then a novel multiple-instance learning framework, named SMILE-SVM (Simulated annealing Multiple Instance LEarning Support Vector Machines), is presented for learning human action detector based on imprecise action locations. SMILE-SVM is extensively evaluated with satisfactory performances on two tasks: 1) human action detection on a public video action database with cluttered backgrounds, and 2) a real world problem of detecting whether the customers in a shopping mall show an intention to purchase the merchandise on shelf (even if they didn't buy it eventually). In addition, the complementary nature of motion and appearance features in action detection are also validated, demonstrating a boosted performance in our experiments.

The existing face detection methods usually had the problem of low accuracy of face recognition in the environment of occlusion interference, which was limited when applied to the face detection task in complex scenes. Therefore, in order to realize high precision and real-time local face recognition in a complex environment, a face local attribute detection method based on improved SSD network structure was proposed. Based on the analysis of the face local attribute detection task, SSD was used as the basic detection network structure, and the VGG16 feature extraction model was used as the framework of face local detection. On this basis, by organically connecting different layers of the SSD network and integrating convolution block attention module, the improved SSD network structure was used to realize face local attribute detection. The proposed model was trained and tested using typical public datasets such as Wider Face, MAFA, and COFW. Experimental results showed that this method had high recognition accuracy, can better detect local features of the human face than other models, and can provide some support for local face attribute detection. This method would provide a theoretical basis and technical support for local face attribute detection in complex scenes.

ABSTRACTDetecting broadband communication signals is crucial for signal processing, as its accuracy directly impacts subsequent processing such as information restoration. However, due to the ever‐growing complexity of the electromagnetic environment, traditional broadband detection algorithms are no longer suitable for current application needs. This paper proposes a broadband signal detection model, NLYOLO. We improve the precision of the image by analysing the characteristics of the target signal by selecting suitable parameters. We also select anchors adapted to the special shape of the target signals and introduce attention modules Non‐local and SimAM in the feature extraction of NLYOLO and improve the loss function. This enhances the ability of high‐level semantic information feature extraction and improves the precision rate and recall of small target signals. The experimental results show that compared with the traditional energy detection algorithm and the baseline model, the detection precision and recall rate are significantly improved, which effectively achieves the target detection task in the field of signal processing in complex scenes.