Improve Object Detection Research Articles

PlantSR: Super-Resolution Improves Object Detection in Plant Images.

Recent advancements in computer vision, especially deep learning models, have shown considerable promise in tasks related to plant image object detection. However, the efficiency of these deep learning models heavily relies on input image quality, with low-resolution images significantly hindering model performance. Therefore, reconstructing high-quality images through specific techniques will help extract features from plant images, thus improving model performance. In this study, we explored the value of super-resolution technology for improving object detection model performance on plant images. Firstly, we built a comprehensive dataset comprising 1030 high-resolution plant images, named the PlantSR dataset. Subsequently, we developed a super-resolution model using the PlantSR dataset and benchmarked it against several state-of-the-art models designed for general image super-resolution tasks. Our proposed model demonstrated superior performance on the PlantSR dataset, indicating its efficacy in enhancing the super-resolution of plant images. Furthermore, we explored the effect of super-resolution on two specific object detection tasks: apple counting and soybean seed counting. By incorporating super-resolution as a pre-processing step, we observed a significant reduction in mean absolute error. Specifically, with the YOLOv7 model employed for apple counting, the mean absolute error decreased from 13.085 to 5.71. Similarly, with the P2PNet-Soy model utilized for soybean seed counting, the mean absolute error decreased from 19.159 to 15.085. These findings underscore the substantial potential of super-resolution technology in improving the performance of object detection models for accurately detecting and counting specific plants from images. The source codes and associated datasets related to this study are available at Github.

Computer Simulation of Rural Landscape Design Based on Remote Sensing Image Technology

Introduction: The field of rural landscape design deals with the design and recovery of rural areas and landscape in a way that it can support natural biodiversity in addition to human needs in sustainable ways as well as maintaining its cultural character. It employs the use of plants, landforms and some water without interference with the environment in order to come up with useful and beautiful spaces. Recognizing the importance of preserving the environment while at the same time investing in developmental projects, it is centralized and focuses on the entire eco-system with the aim of enhancing the lives of the people. Aim: This study aims to develop theoretical aspect of an innovative computer simulation model for designing rural landscapes by applying the technology of remote sensing image. Research methodology: We suggest a new Starling Murmuration search-driven Adaptive YOLOv7 algorithm to identify and categorize several rural buildings and setting types. For the image data, we collected abundant data from several environments using UAV devices to train our proposed model. It is not surprising that our proposed model combined the use of three dimensional (3D) geographic information system (GIS) virtual imaging design model in the simulation of the rural landscape designs. Our recommended model is then extended using SM optimization to improve object detection with YOLOv7. By repeated adjustments of the network parameters in a somewhat similar fashion like flocking, we managed to enhance both accuracy and efficiency. This framework exploits crowdsourcing for delimiting rural buildings and landscapes with high-fidelity. Findings and Conclusion: We implemented our recommended model in Python software. During the phase of evaluation, we evaluate the efficacy of our recommended SM-AYOLOv7 model across a variety of parameters such as precision (91.72%), recall (92.34%), Intersection over Union (IoU) (90.23%), and f1 score (93.64%). Our experimental results precisely indicate that our approach outperforms traditional approaches. We demonstrate significant increases in accuracy and adaptability, especially when adjusting to dynamic configurations.

FEDM: a convolutional neural network based fertilised egg detection model

ABSTRACT 1. The production of goose eggs holds significant economic value on a global scale and the quality of fertilised eggs is crucial for the successful hatching and sustained development of the poultry industry. Developing a low-cost fertilised egg identification system that is suitable for large-scale testing is of great significance. However, existing methods are expensive and have high environmental detection requirements, which limit their promotion. 2. To address this issue, an improved object detection model called FEDM based on YOLOv5 is proposed, which has been shown to be outstanding among nine models. The main network of YOLOv5 is enhanced with the SENet attention mechanism to improve the feature selection capability. The C3_DCNv3 is introduced to enhance the detection ability of blood vessels in the fertilised eggs. The application of Dyhead significantly improved the representation capacity of the object detection head without any computational overhead. The loss function is replaced with MPDIoU to simplify the calculation process. 3. Experimental results from the augmented dataset showed that the average precision of the FEDM reached 96.7%, which is a 5.5% improvement compared to the YOLOv5s model. FEDM exhibited better detection performance on eggs from different shooting angles than the YOLOv5 algorithm and achieves high detection speed. 4. The FEDM secured significant advancement on the detection rate of the fourth day fertilised egg compared to the YOLOv5 algorithm. Based on this result, savings and space utilisation can be made, which has practical application value.

AIMED-Net: An Enhancing Infrared Small Target Detection Net in UAVs with Multi-Layer Feature Enhancement for Edge Computing

In the context of small unmanned aerial vehicles (UAVs), infrared imaging faces challenges such as low quality, difficulty in detecting small targets, high false alarm rates, and computational resource constraints. To address these issues, we introduce AIMED-Net, an enhancing infrared small target detection net in UAVs with multi-layer feature enhancement for edge computing. Initially, the network encompasses a multi-layer feature enhancement architecture for infrared small targets, including a generative adversarial-based shallow-feature enhancement network and a detection-oriented deep-feature enhancement network. Specifically, an infrared image-feature enhancement method is proposed for the shallow-feature enhancement network, employing multi-scale enhancement to bolster target detection performance. Furthermore, within the YOLOv7 framework, we have developed an improved object detection network integrating multiple feature enhancement techniques, optimized for infrared targets and edge computing conditions. This design not only reduces the model’s complexity but also enhances the network’s robustness and accuracy in identifying small targets. Experimental results obtained from the HIT-UAV public dataset indicate that, compared to YOLOv7s, our method achieves a 2.5% increase in F1 score, a 6.1% rise in AP for detecting OtherVehicle targets, and a 2.6% improvement in mAP across all categories, alongside a 15.2% reduction in inference time on edge devices. Compared to existing state-of-the-art approaches, our method strikes a balance between detection efficiency and accuracy, presenting a practical solution for deployment in aerial edge computing scenarios.

DP-DDCL: A discriminative prototype with dual decoupled contrast learning method for few-shot object detection

Few-shot object detection (FSOD) can effectively improve object detection performance with limited training data, attracting increasing interest from researchers. Due to the limited sample size, there is often a large variance in the learned features, resulting in deviating from the class center and being confused with other classes. People are often able to accurately identify few-shot objects based on discriminative information. Motivated by it, we propose a discriminative prototype with dual decoupled contrast learning (DP-DDCL) method to address the issue of limited training data in FSOD. By introducing domain knowledge comprising the CLIP and attribute knowledge graph to obtain explicit and implicit semantic and visual information, we construct a novel discriminative prototype that enhances the representation of different classes (especially few-shot samples). Simultaneously, dual decoupled contrast learning consists of the decoupled of positive and negative samples, and the decoupled of discriminative prototype and instance contrast learning is proposed. It makes samples of the same class cluster around their respective class prototype while maintaining a clear semantic boundary between different classes. Extensive experiments demonstrate the efficacy of our method, surpassing the current state-of-the-art in any-shot and all-data splits, with maximum performance gains of up to +9.15% on the standard PASCAL VOC benchmark and +2.5% on the challenging COCO benchmark.

Filtering Empty Video Frames for Efficient Real-Time Object Detection.

Deep learning models have significantly improved object detection, which is essential for visual sensing. However, their increasing complexity results in higher latency and resource consumption, making real-time object detection challenging. In order to address the challenge, we propose a new lightweight filtering method called L-filter to predict empty video frames that include no object of interest (e.g., vehicles) with high accuracy via hybrid time series analysis. L-filter drops those frames deemed empty and conducts object detection for nonempty frames only, significantly enhancing the frame processing rate and scalability of real-time object detection. Our evaluation demonstrates that L-filter improves the frame processing rate by 31-47% for a single traffic video stream compared to three standalone state-of-the-art object detection models without L-filter. Additionally, L-filter significantly enhances scalability; it can process up to six concurrent video streams in one commodity GPU, supporting over 57 fps per stream, by working alongside the fastest object detection model among the three models.

Maritime distress target detection algorithm based on YOLOv5s‐EFOE network

AbstractTraditional maritime search and rescue methods mainly rely on manual operation, which takes a long time to identify and results in poor search and rescue results. This paper applies computer vision technology to the field of maritime distress object detection and proposes an improved object detection algorithm YOLOv5s‐EFOE based on the YOLOv5s algorithm. Firstly, the authors change the detection head of the YOLOv5s algorithm to use a mixed channel strategy to build a more efficient decoupling head, reducing the number of 3 × 3 convolutional layers in the middle of the decoupling head to only one. The width of the head is scaled by the width multipliers of Backbone and Neck. Secondly, in conjunction with the SimOTA matching algorithm, the positive samples of the target to be tested are dynamically allocated to improve the recognition ability of different targets. Finally, considering the low pixel value of the maritime distress target from the perspective of unmanned aerial vehicles (UAV), the loss function CIoU in the original YOLOv5s is changed to EIoU. EIoU not only considers the distance and aspect ratio of the centre point, but also considers the true difference between the width and height of the prediction box and the real box, which improves the prediction accuracy of the anchor box. Experiments are conducted on a subset of the public dataset SeaDronesSee. The of the YOLOv5s‐EFOE model proposed in this paper reached 75.9%, reached 79.9%, and reached 44.5%. These indicators are superior to the original YOLOv5s model, YOLOv7 series models, and YOLOv8 series models. Compared with the original model, the YOLOv5s‐EFOE model has increased the by 5.4%, by 5.6%, and by 4.6%, improving the difficult to detect and missed detection situations. This model can be deployed on UAVs and can effectively identify maritime distress target, achieving the purpose of search and rescue.

FS-YOLO: Real-time Fire and Smoke Detection based on Improved Object Detection Algorithms

FS-YOLO: Real-time Fire and Smoke Detection based on Improved Object Detection Algorithms

Improved object detection method for unmanned driving based on Transformers.

The object detection method serves as the core technology within the unmanned driving perception module, extensively employed for detecting vehicles, pedestrians, traffic signs, and various objects. However, existing object detection methods still encounter three challenges in intricate unmanned driving scenarios: unsatisfactory performance in multi-scale object detection, inadequate accuracy in detecting small objects, and occurrences of false positives and missed detections in densely occluded environments. Therefore, this study proposes an improved object detection method for unmanned driving, leveraging Transformer architecture to address these challenges. First, a multi-scale Transformer feature extraction method integrated with channel attention is used to enhance the network's capability in extracting features across different scales. Second, a training method incorporating Query Denoising with Gaussian decay was employed to enhance the network's proficiency in learning representations of small objects. Third, a hybrid matching method combining Optimal Transport and Hungarian algorithms was used to facilitate the matching process between predicted and actual values, thereby enriching the network with more informative positive sample features. Experimental evaluations conducted on datasets including KITTI demonstrate that the proposed method achieves 3% higher mean Average Precision (mAP) than that of the existing methodologies.

Real Time Object Detection System Using Yolov

Improving object detection models in computer vision is a crucial area of focus. Object detection represents a more sophisticated approach to image classification, where a neural network identifies objects within an image and delineates them using bounding boxes. YOLO (You Only Look Once) revolutionized object detection by introducing an end-to-end neural network architecture that simultaneously predicts bounding boxes and class probabilities. Unlike earlier methods that adapted classifiers for detection, YOLO's approach streamlines the process by integrating classification and localization tasks, accurately delineating objects with bounding boxes. The project mainly focuses on augmenting YOLOv4, a state-of-the-art object detection architecture, to address the limitations like small object detection, adaptive lighting handling, occlusion challenges, detecting objects at different angles, and specialized object features. Additionally, we aim to improve the model's ability to recognize specialized object features for superior classification. Furthermore, by incorporating functionalities like license plate recognition using Tesseract OCR, object counting (total and class-wise), and detection cropping, this project extends the model's applicability to real-world scenarios. These functionalities make the model valuable in areas like autonomous vehicles, traffic monitoring, and industrial automation. The augmented model's improvements aim to overcome drawbacks identified in existing research, enhancing its efficacy in various scenarios.

An Improved Object Detection Algorithm Based on the Hessian Matrix and Conformable Derivative

An Improved Object Detection Algorithm Based on the Hessian Matrix and Conformable Derivative

AMSP-UOD: When Vortex Convolution and Stochastic Perturbation Meet Underwater Object Detection

In this paper, we present a novel Amplitude-Modulated Stochastic Perturbation and Vortex Convolutional Network, AMSP-UOD, designed for underwater object detection. AMSP-UOD specifically addresses the impact of non-ideal imaging factors on detection accuracy in complex underwater environments. To mitigate the influence of noise on object detection performance, we propose AMSP Vortex Convolution (AMSP-VConv) to disrupt the noise distribution, enhance feature extraction capabilities, effectively reduce parameters, and improve network robustness. We design the Feature Association Decoupling Cross Stage Partial (FAD-CSP) module, which strengthens the association of long and short range features, improving the network performance in complex underwater environments. Additionally, our sophisticated post-processing method, based on non-maximum suppression with aspect-ratio similarity thresholds, optimizes detection in dense scenes, such as waterweed and schools of fish, improving object detection accuracy. Extensive experiments on the URPC and RUOD datasets demonstrate that our method outperforms existing state-of-the-art methods in terms of accuracy and noise immunity. AMSP-UOD proposes an innovative solution with the potential for real-world applications. Our code is available at https://github.com/zhoujingchun03/AMSP-UOD.

Aerial Surveillance Leveraging Delaunay Triangulation and Multiple-UAV Imaging Systems

In aerial surveillance systems, achieving optimal object detection precision is of paramount importance for effective monitoring and reconnaissance. This article presents a novel approach to enhance object detection accuracy through the integration of Delaunay triangulation with multi-unmanned aerial vehicle (UAV) systems. The methodology involves positioning multiple UAVs at pre-specified locations using the Delaunay triangulation algorithm with performance of O (n log n). This is compared with the conventional single UAV approach at a near distance. Our findings reveal that the collaborative efforts of multiple UAVs, guided by Delaunay triangulation, significantly improves object detection accuracy, especially when compared to a single UAV operating in close proximity. This research employs advanced image processing techniques to identify objects in the area under surveillance. Results indicate a substantial enhancement in the collective surveillance capabilities of the multi-UAV system, demonstrating its efficacy in unconstrained scenarios. This research not only contributes to the optimization of aerial surveillance operations but also underscores the potential of spatially informed UAV networks for applications demanding heightened object detection accuracy. The integration of Delaunay triangulation with multi-UAV systems emerges as a promising strategy for advancing the capabilities of aerial surveillance in scenarios ranging from security and emergency response to environmental monitoring.

YOLOv7-DCN-SORT: An algorithm for detecting and counting targets on Acetes fishing vessel operation

The quantification of fishing information on fishing vessels is a prerequisite for implementing refined management of quota-based fishing. In order to address the target detection and information quantification issues in the quota-based fishing of Acetes chinensis, this study installed an Electronic Monitoring (EM) system on Acetes chinensis fishing vessels. Using the EM system video as a data source. Based on YOLOv7, an improved object detection algorithm (YOLOv7-DCN) is proposed. Additionally, drawing on the main ideas of the SORT algorithm, a target counting algorithm is also proposed (YOLOv7-DCN-SORT). YOLOv7-DCN object detection algorithm uses DCNv2 as the backbone network to detect the main targets in fishing vessel operations, improving the network's ability to detect deformable targets. The YOLOv7-DCN-SORT target counting algorithm utilizes the YOLOv7-DCN obtained in the detection phase as the target detection model. It applies the Kalman filter and Hungarian algorithm from the SORT algorithm to track and predict the counted targets. By setting collision detection lines, timestamps, thresholds, and counters, this algorithm can accurately count the number of baskets filled with Acetes chinensis and the number of nets deployed during fishing operations. The results show that: 1) The improved YOLOv7-DCN achieved precision, recall, mAP, and F1-score of 98.21%, 98.43%, 99.19%, and 98.33%, respectively, for each target detection category on the test set. These values represent improvements of 2.06%, 0.64%, 0.08%, and 1.37% compared to the original YOLOv7 model. 2) The YOLOv7-DCN-SORT algorithm achieved counting accuracy rates of 82.00% for counting the number of Acetes chinensis baskets and 96.61% for the number of deployed nets. In summary, this study provides methods for automated recording and intelligent information processing in operations on offshore fishing vessels, serving as a reference for quota-based fishing management decisions.

Strawberry Maturity Recognition Based on Improved YOLOv5

Strawberry maturity detection plays an essential role in modern strawberry yield estimation and robot-assisted picking and sorting. Due to the small size and complex growth environment of strawberries, there are still problems with existing recognition systems’ accuracy and maturity classifications. This article proposes a strawberry maturity recognition algorithm based on an improved YOLOv5s model named YOLOv5s-BiCE. This algorithm model is a replacement of the upsampling algorithm with a CARAFE module structure. It is an improvement on the previous model in terms of its content-aware processing; it also widens the field of vision and maintains a high level of efficiency, resulting in improved object detection capabilities. This article also introduces a double attention mechanism named Biformed for small-target detection, optimizing computing allocation, and enhancing content perception flexibility. Via multi-scale feature fusion, we utilized double attention mechanisms to reduce the number of redundant computations. Additionally, the Focal_EIOU optimization method was introduced to improve its accuracy and address issues related to uneven sample classification in the loss function. The YOLOv5s-BiCE algorithm was better at recognizing strawberry maturity compared to the original YOLOv5s model. It achieved a 2.8% increase in the mean average precision and a 7.4% increase in accuracy for the strawberry maturity dataset. The improved algorithm outperformed other networks, like YOLOv4-tiny, YOLOv4-lite-e, YOLOv4-lite-s, YOLOv7, and Fast RCNN, with recognition accuracy improvements of 3.3%, 4.7%, 4.2%, 1.5%, and 2.2%, respectively. In addition, we developed a corresponding detection app and combined the algorithm with DeepSort to apply it to patrol robots. It was found that the detection algorithm exhibits a fast real-time detection speed, can support intelligent estimations of strawberry yield, and can assist picking robots.

Hair cluster detection model based on dermoscopic images

Introduction: Hair loss has always bothered many people, with numerous individuals potentially facing the issue of sparse hair.Methods: Due to a scarcity of accurate research on detecting sparse hair, this paper proposes a sparse hair cluster detection model based on improved object detection neural network and medical images of sparse hair under dermatoscope to optimize the evaluation of treatment outcomes for hair loss patients. A new Multi-Level Feature Fusion Module is designed to extract and fuse features at different levels. Additionally, a new Channel-Space Dual Attention Module is proposed to consider both channel and spatial dimensions simultaneously, thereby further enhancing the model’s representational capacity and the precision of sparse hair cluster detection.Results: After testing on self-annotated data, the proposed method is proven capable of accurately identifying and counting sparse hair clusters, surpassing existing methods in terms of accuracy and efficiency.Discussion: Therefore, it can work as an effective tool for early detection and treatment of sparse hair, and offer greater convenience for medical professionals in diagnosis and treatment.

RIOD:Reinforced Image-based Object Detection for Unruly Weather Conditions

Deep Neural Network (DNN) object detectors have proved their efficiency in the detection and classification of objects in normal weather. However, these models suffer a lot during bad weather conditions (foggy, rain, haze, night, etc.). This study presents a new scheme to reduce the aforementioned issue by attenuating the noise in the input image before feeding it to any kind of neural network-based object detector. In this study, the image optimization function transforms subpar-quality images due to bad weather into pictures with the optimal possible quality by estimating the proper illumination and transmission function. These optimized images showed improved object detection rates in the YOLOv4 and YOLOv5 models. This improvement in object detection was also noticed in the case of video input. This scheme was tested with images/videos from various weather conditions, and the results showed an encouraging improvement in detection rates.

Panoramic visual system for spherical mobile robots

Abstract Aimed at the challenges of wide-angle mobile robot visual perception for diverse field applications, we present the spherical robot visual system that uses a 360° field of view (FOV) for realizing real-time object detection. The spherical robot image acquisition system model is developed with optimal parameters, including camera spacing, camera axis angle, and the distance of the target image plane. Two 180 $^{\circ}$ -wide panoramic FOVs, front and rear view, are formed using four on-board cameras. The speed of the SURF algorithm is increased for feature extraction and matching. For seamless fusion of the images, an improved fade-in and fade-out algorithm is used, which not only improves the seam quality but also improves object detection performance. The speed of the dynamic image stitching is significantly enhanced by using a cache-based sequential image fusion method. On top of the acquired panoramic wide FOVs, the YOLO algorithm is used for real-time object detection. The panoramic visual system for the spherical robot is then tested in real time, which outputs panoramic views of the scene at an average frame rate of 21.69 fps and panoramic views with object detection at an average of 15.39 fps.

Multitargets Joint Training Lightweight Model for Object Detection of Substation.

The object detection of the substation is the key to ensuring the safety and reliable operation of the substation. The traditional image detection algorithms use the corresponding texture features of single-class objects and would not handle other different class objects easily. The object detection algorithm based on deep networks has generalization, and its sizeable complex backbone limits the application in the substation monitoring terminals with weak computing power. This article proposes a multitargets joint training lightweight model. The proposed model uses the feature maps of the complex model and the labels of objects in images as training multitargets. The feature maps have deeper feature information, and the feature maps of complex networks have higher information entropy than lightweight networks have. This article proposes the heat pixels method to improve the adequate object information because of the imbalance of the proportion between the foreground and the background. The heat pixels method is designed as a kind of reverse network calculation and reflects the object's position to the pixels of the feature maps. The temperature of the pixels indicates the probability of the existence of the objects in the locations. Three different lightweight networks use the complex model feature maps and the traditional tags as the training multitargets. The public dataset VOC and the substation equipment dataset are adopted in the experiments. The experimental results demonstrate that the proposed model can effectively improve object detection accuracy and reduce the time-consuming and calculation amount.

Integration of ShuffleNet V2 and YOLOv5s Networks for a Lightweight Object Detection Model of Electric Bikes within Elevators

The entry of electric bikes into elevators poses safety risks. This article proposes a lightweight object detection model for edge deployment in elevator environments specifically designed for electric bikes. Based on the YOLOv5s network, the backbone network replaces the original CSPDarknet53 with a lightweight multilayer ShuffleNet V2 convolutional neural network, achieving a lightweight backbone network. Swin Transformer modules are introduced between layers to enhance the feature expression capability of images, and a SimAM attention mechanism is applied at the end layer to further improve the feature extraction capability of the backbone network. In the neck network, lightweight and depth-balanced GSConv and VoV-GSCSP modules replace several Conv and C3 basic convolutional modules, reducing the parameter count while enhancing the cross-scale connection and fusion capabilities of feature maps. The prediction network uses the faster-converging and more accurate EIOU error function as the position loss function for iterative training. This article conducts various lightweighting comparison experiments and ablation experiments on the improved object detection model. The experimental results demonstrate that the proposed object detection model, with a model size of only 2.6 megabytes and 1.1 million parameters, achieves a frame rate of 106 frames per second and a detection accuracy of 95.5%. This represents an 84.8% reduction in computational load compared to the original YOLOv5s model. The model’s volume and parameter count are reduced by 81.0% and 84.3%, respectively, with only a 0.9% decrease in mAP. The improved object detection model proposed in this paper can meet the real-time detection requirements for electric bikes in elevator scenarios, providing a feasible technical solution for its deployment on edge devices within elevators.