Lightweight target detection for the field flat jujube based on improved YOLOv5

The ability to detect small targets and the speed of the target detector are very important for the application of remote sensing image detection, and in this paper, we propose an effective and efficient method (named CISPNet) with high detection accuracy and compact architecture. In particular, according to the characteristics of the data, we apply a context information scene perception (CISP) module to obtain the contextual information for targets of different scales and use k-means clustering to set the aspect ratios and size of the default boxes. The proposed method inherits the network structure of Single Shot MultiBox Detector (SSD) and introduces the CISP module into it. We create a dataset in the Pascal Visual Object Classes (VOC) format, annotated with the three types of detection targets, aircraft, ship, and oiltanker. Experimental results on our remote sensing image dataset as well as the Northwestern Polytechnical University very-high-resolution (NWPU VRH-10) dataset demonstrate that the proposed CISPNet performs much better than the original SSD and other detectors especially for small objects. Specifically, our network can achieve 80.34% mean average precision (mAP) at the speed of 50.7 frames per second (FPS) with the input size 300 × 300 pixels on the remote sensing image dataset. On extended experiments, the performance of CISPNet in fuzzy target detection in remote sensing image is better than that of SSD.

Purpose In order to resolve the situation of high missed diagnosis rate and high misdiagnosis rate of the pathological analysis of the gastrointestinal endoscopic images by experts, we propose an automatic polyp detection algorithm based on Single Shot Multibox Detector (SSD). Method In the paper, SSD is based on VGG-16, the fully connected layer is changed to a convolutional layer, and four convolutional layers with successively decreasing scales are added as a new network structure. In order to verify the practicability, it is not only compared with manual polyp detection but also with Mask R-CNN. Results Multiple experimental results show that the mean Average Precision (mAP) of the SSD network is 95.74%, which is 12.4% higher than the manual detection and 5.7% higher than the Mask R-CNN. When detecting a single frame of image, the detection speed of SSD is 8.41 times that of manual detection. Conclusion Based on the traditional pattern recognition algorithm and the target detection algorithm using deep learning, we select a variety of algorithms to identify and classify polyps to achieve efficient detection results. Our research demonstrates that deep learning has a lot of room for development in the field of gastrointestinal image recognition.

We propose a lightweight detection algorithm based on the Single Shot MultiBox Detector (SSD) algorithm in order to facilitate sheep management and to realize sheep facial identification, and we take the self-constructed dataset as the research object. First, the SSD replaces the VGG16 backbone network with MobileNetv3, a lightweight neural network, to create a hybrid model that is much smaller. Second, the ECA attention mechanism is incorporated into the backend of the 72 × 160 bottleneck layer. Finally, the SmoothL1 loss function is substituted with the BalancedL1 loss function. The optimized model’s size decreases significantly from the original SSD’s 132 MB to just 22.4 MB. It achieves a mean average precision of 83.47% and maintains an average frame rate of 68.53 frames per second. Compared to the basic SSD model, the mean average precision has increased by 3.25 percentage points, the model size has decreased by 109.6 MB, and the detection speed has improved by 9.55 frames per second. In comparative experiments using the same dataset with different object detection models, the proposed model outperforms the SSD, Faster R-CNN, Retinanet, and CenterNet in terms of mean average precision, with improvements of 3.25 percentage points, 4.71 percentage points, 2.38 percentage points, and 8.13 percentage points, respectively. The detection speed has shown significant improvements, increasing by 9.55, 58.55, 53.1, and 12.37 frames per second, respectively. The improved model presented in this paper significantly reduces the model’s size and computational requirements while maintaining an excellent performance. This provides a valuable reference for the digitalization of animal husbandry and livestock farming.

Simple SummaryIn the process of breeding geese, manually recording data causes the problems of missing and confusing characterization data; furthermore, manual intervention can lead to the stress response of breeding geese and affect the laying efficiency of breeding geese. In this study, we tried to combine the Internet of things and computer image technology to improve the accuracy of data recording, so as to achieve an accurate correspondence between breeding goose individual data and egg-laying data. Therefore, we developed and tested a breeding egg identification and coding system to realize the selection of high-quality breeding geese. The test results showed that the system realized a correspondence of 97.8% between breeding goose individual data and egg-laying data. The system realized the information recording of breeding geese under nonmanual intervention, realized the correspondence between individual data and egg-laying data, and improved the health and welfare of breeding geese.The selection of breeding geese requires the recording of egg production information to correspond to the identity of the breeding geese. However, due to the special physiological characteristics of breeding geese, manual recording in practice can affect the egg-laying performance of breeding geese and can also lead to problems of missing and confusing individual breeding goose data with the number of eggs laid by the geese. For contactless recording of breeding goose identity and egg production information for high-quality breeding, this paper proposes an Internet of things (IoT)-based breeding egg identification and coding method for the selection of high-quality breeding geese. At the sensing level, we deployed a radiofrequency identification (RFID)-based sensor. Each breeding goose wore a foot ring RFID tag on its leg, and the individual information was read by foot ring RFID readers placed at the bottom of the devices. Individual information was uploaded to the cloud server for database management through structured query language (MySQL). The target detection modules were mounted on top of the devices, and the breeding geese and eggs were detected in the delivery rooms by an improved single-shot multi-box detector (SSD) target detection algorithm. The egg body limit transmission device and contactless coding device were activated only in the case of breeding eggs, and the breeding goose information was printed on the egg bodies in the form of quick response codes (QR codes), which enabled the breeding egg information to correspond with the breeding goose information. An evaluative experiment was performed using a system for the selection of high-quality breeding geese, with web cameras and a cloud monitoring platform. The breeding geese were allowed 14 days to become accustomed to the experimental environment before monitoring began. The evaluative experiment results showed that the pass rate of egg body coding reached 98.25%, the improved SSD algorithm was 8.65% more accurate and 62.6 ms faster than traditional SSD, and the accuracy rate corresponding to the individual information of the breeding geese and the surface information of the goose eggs was 97.8%. The experimental results met the requirements of accurate marking of individual information of breeding geese, which can provide technical support for the selection of high-quality breeding geese.

Most existing target detection models are designed for image targets in natural scenarios and the detection results of small targets in aerial images are less than satisfactory. This paper tries to solve the locating and classification problem of small targets in aerial images from the perspectives of fusion between shallow features and deep features, receptive field enhancement, and a lightweight feature extraction network. To realize accurate detection of small targets in aerial images, on the basis of SSD (Single Shot MultiBox Detector), an aerial image target detection model MF-SSD based on multi-scale feature fusion and receptive field enhancement is proposed. In this model, a feature fusion sub-network is established, in which, the two-level fusion of shallow features and skip-connection fusion of intermediate features are provided. In addition, a multi-branch Inception structure D-Inception based on dilated convolution is utilized to achieve receptive field enhancement, which enables the system to better extract target features and adapt to the scale change of target. To address the increased computational complexity of the model after feature fusion and receptive field enhancement processing, a lightweight convolutional neural network based on Mobilenet is used to replace the basic network, which can not only reduce the complexity of the network model but also maintain high detection precision. The experimental results show that the target detection model MF-SSD can be used to effectively detect small targets in aerial images.KeywordsSmall target detectionFeature fusionReceptive field enhancementLightweight convolutional neural network (CNN)

With the development of the new generation communication system in China, the application of intelligent transportation system is more extensive, which brings higher demands for vehicle flow detection and monitoring. Traditional traffic flow detection modes often cannot meet the high statistical accuracy requirement and high-speed detection simultaneously. Therefore, an improved Inception module is integrated into the single shot multi box detector algorithm. An intelligent vehicle flow detection model is constructed based on the improved single shot multi box detector algorithm. According to the findings, the convergence speed of the improved algorithm was the fastest. When the test sample was the entire test set, the accuracy and precision values of the improved method were 93.6% and 96.0%, respectively, which were higher than all comparison target detection algorithms. The experimental results of traffic flow statistics showed that the model had the highest statistical accuracy, which converged during the training phase. During the testing phase, except for manual statistics, all methods had the lowest statistical accuracy on motorcycles. The average accuracy and precision of the designed model for various types of images were 96.9% and 96.8%, respectively. The calculation speed of this intelligent model was not significantly improved compared to the other two intelligent models, but it was significantly higher than manual monitoring methods. Two experimental data demonstrate that the intelligent vehicle flow detection model designed in this study has higher detection accuracy. The calculation speed has no significant difference compared with the traditional method, which is helpful to the traffic flow management in intelligent transportation system.

The performance of underwater target detection algorithms is affected by poor imaging quality in underwater environments. Due to the arithmetic power limitation of underwater devices, existing deep learning networks are unable to provide efficient detection processes with high detection accuracy. Lightweight CNN models have been actively applied for underwater environment detection, yet their lite feature fusion networks cannot provide effective fusion effects and reduce the detection accuracy. In this paper, a lightweight algorithm based on multi-scale feature fusion was proposed, with the model parameters greatly reduced, improving the target detection accuracy. The forward propagation memory overhead is reduced by using multi-scale shared convolutional kernels and pooling operations to co-construct the query matrix in the Tansformer encoding stage. Then, the feature fusion path is optimized in order to enhance the connection of multi-scale features. A multiscale feature adaptive fusion strategy is used to enhance the detection performance and reduce the dependence on the complex feature extraction network. The feature extraction network is also reparameterized to simplify the operation. Using the UPRC offshore dataset for validation, the study results have demonstrated that the statistical mAP metrics validate the detection accuracy. Compared with SSD, RetinaNet and YOLOv5-s improved by 13%, 8.6%, and 0.8%, while the number of parameters decreased by 76.09%, 89.74%, and 87.67%. In addition, compared with the YOLOv5-lite model algorithm with the same parameter volume, the mAP is improved by 3.8%, which verifies the accuracy and efficiency of the algorithm in this paper.

This paper proposes a complex overlapping pedestrian target detection model based on yolov3 model by multi-scale feature fusion and context-aware mechanism. The SONY A7R3a camera shot the model on campus, and the data set was obtained after editing and collating. There were 358 high-definition videos with a resolution of 1920*1080, and the frame rate was 50HZ, about 179,000 frames. Through testing, this paper finds that compared with Single Shot Multibox Detector (SSD), the detection accuracy of the newly proposed model is slightly improved, the detection accuracy is the same as that of Faster R-CNN, and the detection accuracy of the newly proposed model is slightly worse than that of RetinaNet. However, the detection speed of Yolov3 is more than twice that of Single Shot Multibox Detector, RetinaNet and Faster R-CNN. The input size of Yolov3 is 320*320, and the processing of a single image only needs 22ms, so the detection speed of the simplified Yolov3 tiny is faster.

Timber transportation surveillance is the key and important means of forest resource management. In order to surveille timber transportation in the forest road, we carry out timber transportation vehicle detection from the video of bayonet, with which we propose an improvement of SSD (Single Shot Multibox Detector) based on MXNet. We establish a timber transportation vehicle dataset for training and testing the ResNet50 and Darknet53 with three thresholds. As mAP (mean Average Precision) is closely related to IoU (Intersection over Union), the original calculation of which does not consider overlap and disjoint between prediction box and the ground truth, we find it contributes the major part of error-detection with SSD. Inspired by this, we combine a novel metric loss calculation called GIoU (Generalized Intersection over the Union) with SSD to improve mAP, which is proved to be greatly promoted in timber transportation vehicle detection.

Fish kills are sudden mass mortalities that occur in freshwater and marine systems worldwide. Fish kill surveys are essential for assessing the ecological and economic impacts of fish kill events, but are often labor-intensive, time-consuming, and spatially limited. This study aims to address these challenges by exploring the application of unoccupied aerial systems (or drones) and deep learning techniques for coastal fish carcass detection. Seven flights were conducted using a DJI Phantom 4 RGB quadcopter to monitor three sites with different substrates (i.e., sand, rock, shored Sargassum). Orthomosaics generated from drone imagery were useful for detecting carcasses washed ashore, but not floating or submerged carcasses. Single shot multibox detection (SSD) with a ResNet50-based model demonstrated high detection accuracy, with a mean average precision (mAP) of 0.77 and a mean average recall (mAR) of 0.81. The model had slightly higher average precision (AP) when detecting large objects (>42.24 cm long, AP = 0.90) compared to small objects (≤14.08 cm long, AP = 0.77) because smaller objects are harder to recognize and require more contextual reasoning. The results suggest a strong potential future application of these tools for rapid fish kill response and automatic enumeration and characterization of fish carcasses.

Effective survival analysis is essential for identifying optimal preventive treatments within smart healthcare systems and leveraging digital health advancements; however, existing prediction models face limitations, primarily relying on ensemble classification techniques with suboptimal performance in both target detection and predictive accuracy. To address these gaps, this paper proposes a multimodal framework that integrates enhanced facial feature detection and temporal predictive modeling. For facial feature extraction, this study developed a lightweight face-region convolutional neural network (FRegNet) specialized in detecting key facial components, such as eyes and lips in clinical patients that incorporates a residual backbone (Rstem) to enhance feature representation and a facial path aggregated feature pyramid network for multi-resolution feature fusion; comparative experiments reveal that FRegNet outperforms state-of-the-art target detection algorithms, achieving average precision (AP) of 0.922, average recall of 0.933, mean average precision (mAP) of 0.987, and precision of 0.98–significantly surpassing other mask region-based convolutional neural networks (RCNN) variants, such as mask RCNN-ResNeXt with AP of 0.789 and mAP of 0.957. Based on the extracted facial features and clinical physiological indicators, this study proposes an enhanced temporal encoding-decoding (ETED) model that integrates an adaptive attention mechanism and a gated weighting mechanism to improve predictive performance, with comparative results demonstrating that the ETED variant incorporating facial features (ETEncoding-Decoding-Face) outperforms traditional models, achieving an accuracy of 0.916, precision of 0.850, recall of 0.895, F1 of 0.884, and area under the curve (AUC) of 0.947–outperforming gradient boosting with an accuracy of 0.922, but AUC of 0.669, and other classifiers in comprehensive metrics. The results confirm that the multimodal dataset (facial features + physiological indicators) significantly enhances the prediction accuracy of the seven-day survival conditions of patients. Correlation analysis reveals that chronic health evaluation and mean arterial pressure are positively correlated with survival, while temperature, Glasgow Coma Scale, and fibrinogen are negatively correlated.

This study presents an intelligent moving target to replicate mob attacks and other realistic events in police training to match actual fighting needs. The police intelligent moving target must deploy target detection algorithms on the hardware platform, but the traditional you only look once (YOLO)v8 algorithm has a large framework, which will slow recognition due to the hardware platform’s lack of arithmetic power. In this study, GhostNet network architecture replaces YOLOv8 ′ s backbone network for real‐time target identification, improving recognition speed. The bounding box regression issue in target detection uses the scale invariant intersection over union (SIoU) loss function to increase prediction box overlapping and identification accuracy. Finally, BiFormer uses dynamic sparse attention for more flexible computational allocation and content perception. The method’s real‐time detection speed is 4.81 frames per second (FPS) faster, mAP@0.5 is 5.38% faster, mean average precision (mAP)@0.5:0.95 is 4.19% faster, and parameter volume is 5.81 M less than the original approach. The approach developed in this work has several applications in real‐time target identification and lightweight deployment.

Objective The effects of different algorithms on detecting and tracking moving objects in images based on computer vision technology are studied, and the best algorithm scheme is confirmed. Methods An automatic moving target detection and tracking algorithm based on the improved frame difference method and mean-shift was proposed to test whether the improved algorithm has improved the detection and tracking effect of moving targets. The algorithm improves the traditional three-frame difference method and introduces a single Gaussian background model to participate in target detection. The improved frame difference method is used to detect the target, and the position window and center of the target are determined. Combined with the mean-shift algorithm, it is determined whether the template needs to be updated according to whether it exceeds the set threshold so that the algorithm can automatically track the moving target. Results The position and size of the search window change as the target location and size change. The Bhattacharyya similarity measure ρ (y) exceeds the threshold r, and the target detection algorithm is successfully restarted. Conclusion The algorithm for automatic detection and tracking of moving objects based on the improved frame difference method and mean-shift is fast and has high accuracy.

There are two main approaches to hyperspectral target detection: anomaly detection techniques, which detect outliers substantially different from the background, and spectral signature techniques, which require as an input a user-defined target signature. Oftentimes, however, the target signature may not be known, or there may be unexpected targets in the image, which are unknown but still of interest. As a result, algorithms that can automatically extract potential target signatures without any a priori knowledge are of great interest. In this work, a fusion-based algorithm is developed that takes advantage of both spatial and spectral information to automatically extract the spectral signatures of potential targets of interest. The performance of several target detection algorithms is compared for both the proposed spatially-spectrally estimated (SSE) target signature and the initial target signature used by the Automatic Target Detection and Classification Algorithm (ATDCA). It is shown that the SSE signature leads to improved automatic spectral target recognition (ATSR) performance than the ATDCA algorithm for the test conducted on the AVIRIS Indian Pines dataset.

In infrared (IR) target detection, achieving reliable detection results at high speed is essential. To address the problems of low accuracy, large number of parameters, and complexity of the target detection model for IR images in complex backgrounds, it is difficult to achieve a better balance between accuracy and speed, we propose a YOLO-GCSPNet-efficient dual attention mechanism (EDAM) Attention (YOLO-GEA) IR target detection algorithm. Firstly, to significantly reduce model parameters while maintaining detection accuracy, we designed a lightweight partial multi-scale feature aggregation module (CSP-PMFA). Secondly, we proposed an EDAM, which adaptively learns the importance of each channel and spatial position, thereby better capturing key information in the image. Additionally, we developed the GCSPNet backbone network based on GhostNet and the CSP-PMFA module to optimize the feature aggregation process and achieve model compression. Finally, the WIoUv3 loss function is employed to further improve the precision of bounding box regression. Experiments demonstrate that on the IFdata and FLIR datasets, the mAP@0.5 reached 90.1% and 86.0%, respectively, representing improvements of 3.4% and 1.5% compared to the original YOLOv8, while reducing the number of parameters by 13.0%. Additionally, on the NEU-DET dataset, the mAP@0.5 achieved 79.8%, validating the model’s generalization performance across different datasets.