Target Detection Framework Research Articles

Design of apple recognition model based on improved deep learning object detection framework Faster-RCNN

It the stage of digital economy development in China, intelligent recognition technology is used in agriculture, forestry and planting industries. This paper improves and optimizes apple recognition based on Faster-RCNN, a deep learning target detection framework, and analyzes the advantages and disadvantages of the improved target detection and recognition model. This study compares and analyzes the conventional Faster-RCNN apple recognition model and the enhanced Faster-RCNN apple recognition model design based on the deep learning target detection framework. From the two groups of recognition model systems under different design schemes, the research and analysis of comprehensive performance, sensitivity and coupling shows that the improved Faster-RCNN Apple recognition model has higher accuracy and more accurate positioning for Apple recognition. The results show that the improved Faster-RCNN apple recognition model can more effectively improve the design of the apple recognition model at the present stage, reduce labor costs, and significantly improve work efficiency. It also promotes the development of the domestic digital economy and provides research support and value for future intelligence and deep learning development paths.

Vehicle object detection and ranging in vehicle images based on deep learning

In order to improve the accuracy of vehicle target detection and the stability of ranging in driving environments, a vehicle target detection and ranging method based on deep learning is proposed. The YOLOX-S algorithm is used as the vehicle target detection framework for improvement: the CBAM attention module is introduced on the basis of the original algorithm to enhance the network feature expression ability, and the confidence loss function is replaced by Focal Loss to reduce the training weight of simple samples and improve the attention of positive samples. The vehicle ranging model is established according to the imaging principle and geometric relationship of the vehicle camera, and the ranging feature point coordinates and camera internal parameters are input to obtain the ranging results. The self-made Tlab dataset and BDD 100K dataset are used to train and evaluate the improved YOLOX-S algorithm, and a static ranging experimental scene is built to verify the vehicle ranging model. The experimental results show that the improved YOLOX-S algorithm has a detection speed of 70.14 frames per second on the experimental data set. Compared with the original algorithm, the precision, recall, F1 value, and mAP are improved respectively 0.86%、1.32%、1.09%、1.54% ; within the measurement range of 50 m in the longitudinal direction and 11.25 m in the lateral direction, the average ranging error is kept within 3.20% . It can be seen that the proposed method has good vehicle ranging accuracy and stability while meeting the real-time requirements of vehicle detection.

CECS-CLIP: Fusing Domain Knowledge for Rare Wildlife Detection Model.

Accurate and efficient wildlife monitoring is essential for conservation efforts. Traditional image-based methods often struggle to detect small, occluded, or camouflaged animals due to the challenges posed by complex natural environments. To overcome these limitations, an innovative multimodal target detection framework is proposed in this study, which integrates textual information from an animal knowledge base as supplementary features to enhance detection performance. First, a concept enhancement module was developed, employing a cross-attention mechanism to fuse features based on the correlation between textual and image features, thereby obtaining enhanced image features. Secondly, a feature normalization module was developed, amplifying cosine similarity and introducing learnable parameters to continuously weight and transform image features, further enhancing their expressive power in the feature space. Rigorous experimental validation on a specialized dataset provided by the research team at Northwest A&F University demonstrates that our multimodal model achieved a 0.3% improvement in precision over single-modal methods. Compared to existing multimodal target detection algorithms, this model achieved at least a 25% improvement in AP and excelled in detecting small targets of certain species, significantly surpassing existing multimodal target detection model benchmarks. This study offers a multimodal target detection model integrating textual and image information for the conservation of rare and endangered wildlife, providing strong evidence and new perspectives for research in this field.

UniverDetect: Universal landmark detection method for multidomain X-ray images

Landmark detection using X-ray imaging is vital for disease screening, treatment, and prognosis. It provides a framework for subsequent tasks, including segmentation, classification, and target detection. Existing landmark detection methods exhibit limits with the increasing number of X-ray examiners. Not only they serve specific data types, but also their ability to learn the complete semantic information from this dataset is limited, potentially affecting their widespread adoption. We address these challenges by proposing a universal landmark detection model for multidomain X-ray imaging, UniverDetect. By progressively acquiring local semantic information, global semantic insights, and anatomical structure knowledge at various levels, the model ensured that the detected landmarks were closely aligned with the ground-truth labels. UniverDetect consists of three key components. The landmark detection module (LDM) utilizes a U-net network equipped with our innovative pyramid depthwise separable (PDS) convolution module for initial landmark detection. The landmark refinement module (LRM) integrates a fine-tuning module comprising continuously extended convolution blocks. Finally, the landmark correction module (LCM) incorporates a graph convolutional network (GCN) to rectify offset errors during partial landmark detection. An inherent feature of this model is its domain- generalization capability, which enables continuous learning across diverse domains. This model can concurrently learn from eight domains, covering 118 landmarks within a diverse dataset of 5969 images. Extensive experiments on multiple datasets demonstrate that this method consistently outperforms state-of-the-art approaches. This study presents a versatile and effective solution to reduce doctors’ workload while providing precise quantitative analysis.

Road Target Detection in Different Weather Conditions Based on Deep Learning

AbstractAddressing the challenge of ensuring robustness in vision‐based target recognition algorithms under adverse weather conditions, such as rain, snow, and fog, is crucial. In this paper, we introduce a novel approach for road target detection that can effectively operate under various weather conditions. Our method is based on the cascade task framework of target detection, complemented by image restoration techniques. Specifically, we have developed a denoising network tailored to meet the demands of de‐raining and snow removal tasks. This network leverages prior knowledge about the mask, enhancing its effectiveness. In real‐world scenarios featuring fog, wet conditions, and snow‐covered roads, our proposed method demonstrates a significant improvement in both recall rate and accuracy compared to conventional single‐object detection algorithms. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

An efficient and lightweight small target detection framework for vision-based autonomous road cleaning

An efficient and lightweight small target detection framework for vision-based autonomous road cleaning

Exploring an application-oriented land-based hyperspectral target detection framework based on 3D–2D CNN and transfer learning

Target detection based on hyperspectral images refers to the integrated use of spatial information and spectral information to accomplish the task of localization and identification of targets. There are two main methods for hyperspectral target detection: supervised and unsupervised methods. Supervision method refers to the use of spectral differences between the target to be tested and the surrounding background to identify the target when the target spectrum is known. In ideal situations, supervised object detection algorithms perform better than unsupervised algorithms. However, the current supervised object detection algorithms mainly have two problems: firstly, the impact of uncertainty in the ground object spectrum, and secondly, the universality of the algorithm is poor. A hyperspectral target detection framework based on 3D–2D CNN and transfer learning was proposed to solve the problems of traditional supervised methods. This method first extracts multi-scale spectral information and then preprocesses hyperspectral images using multiple spectral similarity measures. This method not only extracts spectral features in advance, but also eliminates the influence of complex environments to a certain extent. The preprocessed feature maps are used as input for 3D–2D CNN to deeply learn the features of the target, and then, the softmax method is used to output and obtain the detection results. The framework draws on the ideas of integrated learning and transfer learning, solves the spectral uncertainty problem with the combined similarity measure and depth feature extraction network, and solves the problem of poor robustness of traditional algorithms by model migration and parameter sharing. The area under the ROC curve of the proposed method has been increased to over 0.99 in experiments on both publicly available remote sensing hyperspectral images and measured land-based hyperspectral images. The availability and stability of the proposed method have been demonstrated through experiments. A feasible approach has been provided for the development and application of specific target detection technology in hyperspectral images under different backgrounds in the future.

Lightweight Saliency Target Intelligent Detection based on Multi-scale Feature Adaptive Fusion

In order to solve the problems of small targets, variable shooting angles, and heights in drone images, the author proposes an adaptive drone target intelligent detection algorithm based on multi-scale feature fusion. The results show that after adding a deconvolution cascade structure to the network, mAP increased by about 2.5 percentage points and AP$^{50}$ increased by about 3 percentage points. Compared with Method 3, Method 4 uses GA-RPN instead of RPN, and when the IOU is 75, the AP increases by 3.5 percentage points, reflecting that the target prediction candidate boxes generated using semantic features adaptively match better than the manually designed target candidate boxes. This indicates that the proposed target detection framework has better classification ability and higher frame regression accuracy. Multi scale adaptive candidate regions are used to generate fused features of different scales generated by the network, weighted fused multi-scale features are used for target prediction, and semantic features are used to guide the network to adaptively generate target candidate frames, greatly enhancing the feature expression ability of various targets and improving the detection accuracy of aerial targets.

Framework for Autonomous UAV Navigation and Target Detection in Global-Navigation-Satellite-System-Denied and Visually Degraded Environments

Autonomous Unmanned Aerial Vehicles (UAVs) have possible applications in wildlife monitoring, disaster monitoring, and emergency Search and Rescue (SAR). Autonomous capabilities such as waypoint flight modes and obstacle avoidance, as well as their ability to survey large areas, make UAVs the prime choice for these critical applications. However, autonomous UAVs usually rely on the Global Navigation Satellite System (GNSS) for navigation and normal visibility conditions to obtain observations and data on their surrounding environment. These two parameters are often lacking due to the challenging conditions in which these critical applications can take place, limiting the range of utilisation of autonomous UAVs. This paper presents a framework enabling a UAV to autonomously navigate and detect targets in GNSS-denied and visually degraded environments. The navigation and target detection problem is formulated as an autonomous Sequential Decision Problem (SDP) with uncertainty caused by the lack of the GNSS and low visibility. The SDP is modelled as a Partially Observable Markov Decision Process (POMDP) and tested using the Adaptive Belief Tree (ABT) algorithm. The framework is tested in simulations and real life using a navigation task based on a classic SAR operation in a cluttered indoor environment with different visibility conditions. The framework is composed of a small UAV with a weight of 5 kg, a thermal camera used for target detection, and an onboard computer running all the computationally intensive tasks. The results of this study show the robustness of the proposed framework to autonomously explore and detect targets using thermal imagery under different visibility conditions. Devising UAVs that are capable of navigating in challenging environments with degraded visibility can encourage authorities and public institutions to consider the use of autonomous remote platforms to locate stranded people in disaster scenarios.

A Joint Framework for Underwater Hyperspectral Image Restoration and Target Detection With Conditional Diffusion Model

A Joint Framework for Underwater Hyperspectral Image Restoration and Target Detection With Conditional Diffusion Model

CNN and Binocular Vision-Based Target Detection and Ranging Framework of Intelligent Railway System

CNN and Binocular Vision-Based Target Detection and Ranging Framework of Intelligent Railway System

Attention Mechanism and Detection Box Information Based Real-time Multi-Object Vehicle Detection

Ensuring both the accuracy of vehicle target detection and meeting real-time requirements is crucial in traffic videos. The YOLOv5s target detection framework, known for its accuracy and efficiency, has attracted attention in academic circles. However, there are still some features that can be optimized. First of all, the detection subnet of the YOLOv5s framework cannot smoothly convert complex feature maps into relatively sparse target prediction boxes. To solve this, we integrate a self-attention-based gating mechanism into the detection subnet, forming the YOLOv5s-SAG network. Secondly, the loss function of CIoU used by YOLOv5s pays insufficient attention to the overlapping area of the detection frame, which can be used as metric for measuring target detection effectiveness. We add the loss term of area ratio to CIoU to further improve the modeling ability. Finally, the current multi-class Non-Maximum Suppression algorithm can cause high overlap of multi-class detection frames. To improve it, we propose a multi-class CS-NMS algorithm based on category suppression. Experimental results show an approximately 8% improvement in the mAP50 index on the UA-DETRAC dataset compared with YOLOv5s. The proposed algorithm also achieves better detection results compared to mainstream target detection algorithms and meets the real-time requirements of traffic video analysis.

MFF-Net: Multiscale feature fusion semantic segmentation network for intracranial surgical instruments.

In robot-assisted surgery, automatic segmentation of surgical instrument images is crucial for surgical safety. The proposed method addresses challenges in the craniotomy environment, such as occlusion and illumination, through an efficient surgical instrument segmentation network. The network uses YOLOv8 as the target detection framework and integrates a semantic segmentation head to achieve detection and segmentation capabilities. A concatenation of multi-channel feature maps is designed to enhance model generalisation by fusing deep and shallow features. The innovative GBC2f module ensures the lightweight of the network and the ability to capture global information. Experimental validation of the intracranial glioma surgical instrument dataset shows excellent performance: 94.9% MPA score, 89.9% MIoU value, and 126.6 FPS. According to the experimental results, the segmentation model proposed in this study has significant advantages over other state-of-the-art models. This provides a valuable reference for the further development of intelligent surgical robots.

End-to-end Remote Sensing Image Aircraft Target Detection and Fine-grained Recognition Framework

In view of the practical application of target detection and recognition tasks for remote sensing, an end-to-end aircraft target detection and fine-grained recognition framework is proposed. It can accurately and quickly implement detection and recognition in an end-to-end way. The main network of the framework adopts the design ideas of target detection and fine-grained recognition methods using candidate region extract and visual attention, making sure the accuracy of detection and recognition. Then, to solve the problem of high false detection rate and missed detection rate of densely arranged targets, we propose the re-detection mechanism. To minimize the large amounts of calculations of deep networks and improve real-time performance, we introduce depthwise separable convolution to optimize networks. Finally, a weight mapping idea based on transfer learning is adopted to solve the problem of data labeling and also helps the detection and fine-grained recognition. The results prove that the proposed framework has good robustness, versatility, and efficiency in aircraft detection and fine-grained recognition tasks.

Marine target detection for PPI images based on YOLO-SWFormer

For the task of detecting marine targets, numerous machine-learning methods have been suggested, which can achieve comparable accuracy. Despite the successful application of deep learning in the field of marine target detection in recent years, existing detection methods face challenges due to the significant interference of sea clutter. As artificial intelligence technology advances, the Swin Transformer can serve as an effective backbone for extracting discriminative features. However, it has not yet been utilized for target detection, and the combination of Swin Transformer and YOLO architecture has not been applied to similar missions. In light of this, we propose a novel method, YOLO-SWFormer, which combines the Swin Transformer and YOLO framework for target detection. Our method can extract discriminative features from plan-position indicator (PPI) images despite the interference of sea clutter, thereby reducing computational complexity and enhancing target detection accuracy. Experimental results on a Sea Clutter Database demonstrates that our method surpasses existing methods in terms of accuracy, indicating its potential as a promising solution for marine target detection tasks.

Cross-domain car detection model with integrated convolutional block attention mechanism

Car detection, especially through camera vision, has become a major focus in the field of computer vision and has gained widespread adoption. While current car detection systems are capable of achieving good detection performance, reliable detection can still be challenging due to factors such as car proximity, varying light conditions, and environmental visibility. To address these issues, we propose Cross-Domain Car Detection Model with integrated convolutional block Attention mechanism(CDCDMA) that is specifically designed for car recognition in autonomous driving and related domains. CDCDMA includes several novelties: 1)Building a complete cross-domain target detection framework. 2)Developing an unpaired target domain picture generation module with an integrated convolutional attention mechanism which specifically emphasizes the car headlights feature. 3)Adopting Generalized Intersection over Union (GIOU) as the loss function of the target detection framework. 4)Designing an object detection model integrated with two-headed Convolutional Block Attention Module(CBAM). To evaluate the model's effectiveness, we performed experiments on the SODA 10 M and BDD100K datasets by applying a reduced resolution process to the data, which served as our benchmark dataset for the task. The experimental results demonstrate that the performance of the cross-domain car target detection model improves by 40% compared to the model without our CDCDMA framework. Moreover, our improvements have a significant impact on cross-domain car recognition, surpassing the performance of most advanced cross-domain models.

Target detection for remote sensing based on the enhanced YOLOv4 with improved BiFPN

To solve problems for false detection, inadequate regression performance of anchor frames, and the inability to detect small targets in traditional multiscale target detection methods based on YOLOv4, we propose a novel target detection framework named as Enhanced YOLOv4. Firstly, our improved BiFPN replaced the original PANet as the feature fusion module, which can achieve multi-scale feature fusion by way of shared weights. Secondly, the channel attention mechanism (CAM) was embedded before the detection head to highlight the correlation between channels so that small targets can be get more attention. At last, to improve the anchor box regression effect and accelerate the training speed of YOLOv4, we improved the net training loss function, in which the original CIoU was replaced by CDIoU. The experimental results on the DOTA dataset validate our improvement. The mAP of our method is 90.88%, and the frame rate reached 58.76 FPS, at the same time, the speed of detection is not affected significantly.

Moving Point Target Detection Based on Temporal Transient Disturbance Learning in Low SNR

Moving target detection in optical remote sensing is important for satellite surveillance and space target monitoring. Here, a new moving point target detection framework under a low signal-to-noise ratio (SNR) that uses an end-to-end network (1D-ResNet) to learn the distribution features of transient disturbances in the temporal profile (TP) formed by a target passing through a pixel is proposed. First, we converted the detection of the point target in the image into the detection of transient disturbance in the TP and established mathematical models of different TP types. Then, according to the established mathematical models of TP, we generated the simulation TP dataset to train the 1D-ResNet. In 1D-ResNet, the structure of CBR-1D (Conv1D, BatchNormalization, ReLU) was designed to extract the features of transient disturbance. As the transient disturbance is very weak, we used several skip connections to prevent the loss of features in the deep layers. After the backbone, two LBR (Linear, BatchNormalization, ReLU) modules were used for further feature extraction to classify TP and identify the locations of transient disturbances. A multitask weighted loss function to ensure training convergence was proposed. Sufficient experiments showed that this method effectively detects moving point targets with a low SNR and has the highest detection rate and the lowest false alarm rate compared to other benchmark methods. Our method also has the best detection efficiency.

MIoP-NMS: Perfecting crops target detection and counting in dense occlusion from high-resolution UAV imagery

When performing dense crops target detection and counting tasks in high-resolution images of large scene, several algorithms such as the standard Non-Maximum Suppression (NMS) and its improved CIoU-NMS and soft-NMS are commonly used to improve the de-duplication performance of the prediction frame in objects detection, which has a high mean average precision (mAP) but the error boundaries may be large. In this research, an improved NMS-based max intersection over portion (MIoP-NMS) algorithm is proposed to address this problem and implemented in the YOLOv4 network framework for single-stage target detection. Using banana tree target detection statistics with different sparsity levels as an experimental case, the mAP obtained by applying the method in the paper reaches about 85%, with a mean counting error of about 1.3%. In comparison with several commonly NMS methods, their mAP values are comparable. However, compared to the 10%∼25% mean count error when using these commonly used methods, the mean count error of the method proposed in the paper is reduced by about 8.7%∼23.7%. The method in the paper estimates the number of banana trees in dense occluded banana forests with about 98.7% accuracy, which is simple and effective, and has significant advantages for accurate detection and counting of dense crops targets in high-resolution images in large scenes.

A Transfer-Based Framework for Underwater Target Detection from Hyperspectral Imagery

The detection of underwater targets through hyperspectral imagery is a relatively novel topic as the assumption of target background independence is no longer valid, making it difficult to directly detect underwater targets using land target information. Meanwhile, deep-learning-based methods have faced challenges regarding the availability of training datasets, especially in underwater conditions. To solve these problems, a transfer-based framework is proposed in this paper, which exploits synthetic data to train deep-learning models and transfers them to real-world applications. However, the transfer becomes challenging due to the imparity in the distribution between real and synthetic data. To address this dilemma, the proposed framework, named the transfer-based underwater target detection framework (TUTDF), first divides the domains using the depth information, then trains models for different domains and develops an adaptive module to determine which model to use. Meanwhile, a spatial–spectral process is applied prior to detection, which is devoted to eliminating the adverse influence of background noise. Since there is no publicly available hyperspectral underwater target dataset, most of the existing methods only run on simulated data; therefore, we conducted expensive experiments to obtain datasets with accurate depths and use them for validation. Extensive experiments verify the effectiveness and efficiency of TUTDF in comparison with traditional methods.