Object Detection Algorithm Research Articles

Adaptive occlusion object detection algorithm based on OL-IoU.

The continuous advancement of autonomous driving technology imposes higher demands on the accuracy of target detection in complex environments, particularly when traffic targets are occluded. Existing algorithms still face significant challenges in detection accuracy and real-time performance under such conditions. To address this issue, this paper proposes an improved YOLOX algorithm based on adaptive deformable convolution, named OCC-YOLOX. This algorithm enhances the feature extraction network's ability to focus on occluded targets by incorporating a coordinate attention mechanism. Additionally, it introduces the Overlapping IoU (OL-IoU) loss function to optimize the overlap between predicted and ground truth bounding boxes, thereby improving detection accuracy. Furthermore, the adoption of Fast Spatial Pyramid Pooling (Fast SPP) reduces computational complexity while maintaining real-time performance. Experiments on fused public datasets demonstrate that OCC-YOLOX achieves improvements in accuracy, recall, and average precision by 2.76%, 1.25%, and 1.92%, respectively. In addition to testing on the KITTI, CityPersons, and BDD100K datasets, the effectiveness of the OCC-YOLOX algorithm is further validated through comparisons with self-collected occlusion scene data. The experimental results indicate that OCC-YOLOX outperforms existing mainstream detection algorithms, particularly in handling complex occlusion scenarios, significantly enhancing the accuracy and efficiency of object detection. This study provides new insights for addressing the challenges of occluded target detection in intelligent transportation systems.

Enhancing wildfire detection: a novel algorithm for controllable generation of wildfire smoke images

Background The lack of wildfire smoke image data is one of the most important factors hindering the development of image-based wildfire detection. Smoke image generation based on image inpainting techniques is a solution worthy of study. However, it is difficult to generate smoke texture with context consistency in complex backgrounds with current image inpainting methods. Aims This work aims to provide a wildfire smoke image database for specific scenarios. Methods We designed an algorithm based on generative adversarial networks (GANs) to generate smoke images. The algorithm includes a multi-scale fusion module to ensure consistency between the generated smoke and backgrounds. Additionally, a local feature-matching mechanism in the discriminator guides the generator to capture real smoke’s feature distribution. Key results We generated 13,400 wildfire smoke images based on forest background images and early fire simulation from the Fire Dynamics Simulator (FDS). Conclusions A variety of advanced object detection algorithms were trained based on the generated data. The experimental results confirmed that the addition of the generated data to the real datasets can effectively improve model performance. Implications This study paves a way for generating object datasets to enhance the reliability of watchtower or satellite wildfire monitoring.

Overview of object detection based on deep learning

Abstract. 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.

A Refined and Efficient CNN Algorithm for Remote Sensing Object Detection

Remote sensing object detection (RSOD) plays a crucial role in resource utilization, geological disaster risk assessment and urban planning. Deep learning-based object-detection algorithms have proven effective in remote sensing image studies. However, accurate detection of objects with small size, dense distribution and complex object arrangement remains a significant challenge in the remote sensing field. To address this, a refined and efficient object-detection algorithm (RE-YOLO) has been proposed in this paper for remote sensing images. Initially, a refined and efficient module (REM) was designed to balance computational complexity and feature-extraction capabilities, which serves as a key component of the RE_CSP block. RE_CSP block efficiently extracts multi-scale information, overcoming challenges posed by complex backgrounds. Moreover, the spatial extracted attention module (SEAM) has been proposed in the bottleneck of backbone to promote representative feature learning and enhance the semantic information capture. In addition, a three-branch path aggregation network (TBPAN) has been constructed as the neck network, which facilitates comprehensive fusion of shallow positional information and deep semantic information across different channels, enabling the network with a robust ability to capture contextual information. Extensive experiments conducted on two large-scale remote sensing datasets, DOTA-v1.0 and SCERL, demonstrate that the proposed RE-YOLO outperforms state-of-the-art other object-detection approaches and exhibits a significant improvement in generalization ability.

Enhanced lightweight infrared object detection algorithm for assistive navigation in visually impaired individuals

Enhanced lightweight infrared object detection algorithm for assistive navigation in visually impaired individuals

Underwater Object Detection Algorithm Based on an Improved YOLOv8

Due to the complexity and diversity of underwater environments, traditional object detection algorithms face challenges in maintaining robustness and detection accuracy when applied underwater. This paper proposes an underwater object detection algorithm based on an improved YOLOv8 model. First, the introduction of CIB building blocks into the backbone network, along with the optimization of the C2f structure and the incorporation of large-kernel depthwise convolutions, effectively enhances the model’s receptive field. This improvement increases the capability of detecting multi-scale objects in complex underwater environments without adding a computational burden. Next, the incorporation of a Partial Self-Attention (PSA) module at the end of the backbone network enhances model efficiency and optimizes the utilization of computational resources while maintaining high performance. Finally, the integration of the Neck component from the Gold-YOLO model improves the neck structure of the YOLOv8 model, facilitating the fusion and distribution of information across different levels, thereby achieving more efficient information integration and interaction. Experimental results show that YOLOv8-CPG significantly outperforms the traditional YOLOv8 in underwater environments. Precision and Recall show improvements of 2.76% and 2.06%. Additionally, mAP50 and mAP50-95 metrics have increased by 1.05% and 3.55%, respectively. Our approach provides an efficient solution to the difficulties encountered in underwater object detection.

Dual-branch network object detection algorithm based on dual-modality fusion of visible and infrared images

Dual-branch network object detection algorithm based on dual-modality fusion of visible and infrared images

Real Time Object Detection Algorithm in Foggy Weather Based on WVIT-YOLO Model

Introduction: To address the challenges of low visibility, object recognition difficulties, and low detection accuracy in foggy weather, this paper introduces the WViT-YOLO real-time fog detection model, built on the YOLOv5 framework. The NVIT-Net backbone network, incorporating NTB and NCB modules, enhances the model's ability to extract both global and local features from images. Method: An efficient convolutional C3_DSConv module is designed and integrated with channel attention mechanisms and ShuffleAttention at each upsampling stage, improving the model's computational speed and its ability to detect small and blurry objects. The Wise-IOU loss function is utilized during the prediction stage to enhance the model's convergence efficiency. Result: Experimental results on the publicly available RTTS dataset for vehicle detection in foggy conditions demonstrate that the WViT-YOLO model achieves a 3.2% increase in precision, a 9.5% rise in recall, and an 8.6% improvement in mAP50 compared to the baseline model. Furthermore, WViT-YOLO shows a 9.5% and 8.6% mAP50 improvement over YOLOv7 and YOLOv8, respectively. For detecting small and blurry objects in foggy conditions, the model demonstrates approximately a 5% improvement over the benchmark, significantly enhancing the detection network's generalization ability under foggy conditions. Conclusion: This advancement is crucial for improving vehicle safety in such weather. The code is available at https://github.com/QinghuaZhang1/mode.

Efficient Small Object Detection You Only Look Once: A Small Object Detection Algorithm for Aerial Images.

Aerial images have distinct characteristics, such as varying target scales, complex backgrounds, severe occlusion, small targets, and dense distribution. As a result, object detection in aerial images faces challenges like difficulty in extracting small target information and poor integration of spatial and semantic data. Moreover, existing object detection algorithms have a large number of parameters, posing a challenge for deployment on drones with limited hardware resources. We propose an efficient small-object YOLO detection model (ESOD-YOLO) based on YOLOv8n for Unmanned Aerial Vehicle (UAV) object detection. Firstly, we propose that the Reparameterized Multi-scale Inverted Blocks (RepNIBMS) module is implemented to replace the C2f module of the Yolov8n backbone extraction network to enhance the information extraction capability of small objects. Secondly, a cross-level multi-scale feature fusion structure, wave feature pyramid network (WFPN), is designed to enhance the model's capacity to integrate spatial and semantic information. Meanwhile, a small-object detection head is incorporated to augment the model's ability to identify small objects. Finally, a tri-focal loss function is proposed to address the issue of imbalanced samples in aerial images in a straightforward and effective manner. In the VisDrone2019 test set, when the input size is uniformly 640 × 640 pixels, the parameters of ESOD-YOLO are 4.46 M, and the average mean accuracy of detection reaches 29.3%, which is 3.6% higher than the baseline method YOLOv8n. Compared with other detection methods, it also achieves higher detection accuracy with lower parameters.

Adaptation of Object Detection Algorithms for Road Indicator Lights in Complex Scenes

In the realm of autonomous driving, practical driving scenarios are fraught with numerous complexities, including inclement weather conditions, nighttime blurriness, and ambient light sources that significantly hinder drivers’ ability to discern road indicators. Furthermore, the dynamic nature of road indicators, which are constantly evolving, poses additional challenges for computer vision-based detection systems. To address these issues, this paper introduces a road indicator light detection model, leveraging the advanced capabilities of YOLOv8. We have ingeniously integrated the robust backbone of YOLOv8 with four distinct attention mechanism modules—Convolutional Block Attention Module (CBAM), Efficient Channel Attention (ECA), Shuffle Attention (SA), and Global Attention Mechanism (GAM)—to significantly enhance the model performance in capturing nuanced features of road indicators and boosting the accuracy of detecting minute objects. Additionally, we employ the Asymptotic Feature Pyramid Network (AFPN) strategy, which optimizes the fusion of features across different scales, ensuring not only an enhanced performance but also maintaining real-time capability. These innovative attention modules empower the model by recalibrating the significance of both channel and spatial dimensions within the feature maps, enabling it to hone in on the most pertinent object characteristics. To tackle the challenges posed by samples rich in small, occluded, background-similar objects, and those that are inherently difficult to recognize, we have incorporated the Focaler-IOU loss function. This loss function deftly reduces the contribution of easily detectable samples to the overall loss, thereby intensifying the focus on challenging samples. This strategic balancing of hard-to-detect versus easy-to-detect samples effectively elevates the model’s detection performance. Experimental evaluations conducted on both a public traffic signal dataset and a proprietary headlight dataset have yielded impressive results, with both mAP50 and mAP50:95 metrics experiencing significant improvements exceeding two percentage points. Notably, the enhancements observed in the headlight dataset are particularly profound, signifying a significant step forward toward realizing safer and more reliable assisted driving technologies.

Synthetic thermal image generation and processing for close proximity operations

The new scenarios foreseen in forthcoming space missions have increased interest towards optical-based relative navigation techniques, which have demonstrated efficacy in a variety of operational conditions. Although object detection methods have predominantly been used within the visible spectrum, optical payloads struggle in weak lighting conditions and are susceptible to overexposure. Consequently, thermal imaging systems are being investigated as a potential solution, as their integration into the current systems would greatly extend future mission capabilities. This study seeks to fill the gap in literature by assessing the performance of state-of-the-art object detection algorithms with images captured in the thermal spectrum. Given the scarcity of readily available thermal infrared (TIR) images captured in orbit, a novel rendering pipeline is implemented to generate physically accurate thermal images relevant to close-proximity scenarios. These synthetic representations feature a simplified target spacecraft against Earth and deep space backgrounds, including variations in illumination conditions, material properties, relative state, and scale. To ensure realistic outputs, the radiative field of the Earth is modelled based on satellite measurements collected in the cloud and Earth radiant energy system (CERES) database. To enrich the fidelity of the outputs, a thermal sensor model and the corresponding noise levels are introduced in the pipeline. The generated images are then used to test the performance of traditional object detection algorithms in discerning the region of interest (ROI) under different orbital scenarios. The results demonstrate the effectiveness of the selected methodologies in mitigating the influence of the Earth in the ROI extraction process, while also revealing a performance degradation due to the presence of multi-material targets.

Salient Object Detection From Arbitrary Modalities.

Toward desirable saliency prediction, the types and numbers of inputs for a salient object detection (SOD) algorithm may dynamically change in many real-life applications. However, existing SOD algorithms are mainly designed or trained for one particular type of inputs, failing to be generalized to other types of inputs. Consequentially, more types of SOD algorithms need to be prepared in advance for handling different types of inputs, raising huge hardware and research costs. Differently, in this paper, we propose a new type of SOD task, termed Arbitrary Modality SOD (AM SOD). The most prominent characteristics of AM SOD are that the modality types and modality numbers will be arbitrary or dynamically changed. The former means that the inputs to the AM SOD algorithm may be arbitrary modalities such as RGB, depths, or even any combination of them. While, the latter indicates that the inputs may have arbitrary modality numbers as the input type is changed, e.g. single-modality RGB image, dual-modality RGB-Depth (RGB-D) images or triple-modality RGB-Depth-Thermal (RGB-D-T) images. Accordingly, a preliminary solution to the above challenges, i.e. a modality switch network (MSN), is proposed in this paper. In particular, a modality switch feature extractor (MSFE) is first designed to extract discriminative features from each modality effectively by introducing some modality indicators, which will generate some weights for modality switching. Subsequently, a dynamic fusion module (DFM) is proposed to adaptively fuse features from a variable number of modalities based on a novel Transformer structure. Finally, a new dataset, named AM-XD, is constructed to facilitate research on AM SOD. Extensive experiments demonstrate that our AM SOD method can effectively cope with changes in the type and number of input modalities for robust salient object detection. Our code and AM-XD dataset will be released on https://github.com/nexiakele/AMSODFirst.

CSGO: A Deep Learning Pipeline for Whole-Cell Segmentation in Hematoxylin and Eosin Stained Tissues

Accurate whole-cell segmentation is essential in various biomedical applications, particularly in studying the tumor microenvironment (TME). Despite advancements in machine learning for nuclei segmentation in hematoxylin and eosin (H&E) stained images, there remains a need for effective whole-cell segmentation methods. This study aims to develop a deep learning-based pipeline to automatically segment cells in H&E-stained tissues, thereby advancing the capabilities of pathological image analysis. The Cell Segmentation with Globally Optimized boundaries (CSGO) framework integrates nuclei and membrane segmentation algorithms, followed by post-processing using an energy-based watershed method. Specifically, we employed the You Only Look Once (Yolo) object detection algorithm for nuclei segmentation and U-Net for membrane segmentation. The membrane detection model was trained on a dataset of 7 hepatocellular carcinomas and 11 normal liver tissue patches. The cell segmentation performance was extensively evaluated on five external datasets, including liver, lung, and oral disease cases. CSGO demonstrated superior performance over the state-of-the-art method Cellpose, achieving higher F1 scores ranging from 0.37 to 0.53 at an intersection over union (IoU) threshold of 0.5 in four of the five external datasets, compared to that of Cellpose from 0.21 to 0.36. These results underscore the robustness and accuracy of our approach in various tissue types. A web-based application is available at https://ai.swmed.edu/projects/csgo, providing a user-friendly platform for researchers to apply our method to their own datasets. Our method exhibits remarkable versatility in whole-cell segmentation across diverse cancer subtypes, serving as an accurate and reliable tool to facilitate TME studies. The advancements presented in this study have the potential to significantly enhance the precision and efficiency of pathological image analysis, contributing to better understanding and treatment of cancer.

Using Semi-supervised Machine Learning to Assist Classification and Recognition of Chinese Vernacular Architecture

In order to construct a more refined, comprehensive and systematized classification system for Chinese vernacular architecture, this paper proposed a classifying method based on semi-supervised machine learning using architecture image data. By adding type labels based on experts' prior knowledge as a guide to part of the training samples, it allows generalized machine clustering to effectively combine image feature mining with characteristics of special objects. Taking the scheme of machine clustering as a reference, a classification system for Chinese vernacular architecture with 9 major categories and 23 subcategories was established, which boasts extensive coverage of vernacular architectural types and has strong distinguishability. This method integrates the advantages of expert knowledge and computer algorithm, and can be utilized as a reference for studies where unsupervised or fully supervised machine learning is challenging to apply. In addition, the YOLOv8 object detection algorithm of deep learning is also applied to construct a corresponding recognition model for these architectural categories, which performs well in terms of recognition accuracy and robustness. This tool holds significant potential for application in heritage protection and urban and rural planning.

Autonomous Drone Navigation Using Computer Vision

Abstract: Autonomous drone navigation with computer vision is an innovative technology that allows drones to move through intricate surroundings without needing human control. This system uses live visual information to identify objects, steer clear of obstacles, and determine routes, improving operational safety and precision. The project's main objective is to create a visionbased navigation system that combines object detection and obstacle avoidance algorithms through deep learning methods like YOLO (You Only Look Once), alongside real-time sensor fusion. The drone uses computer vision algorithms to process aerial images and automatically changes its flight path to prevent crashes. A personalized dataset of aerial images is generated and utilized for improving object detection skills in various environments. In order to guarantee practicality in real- world situations, the system undergoes validation through simulations and field tests on different terrains, focusing on its resilience in changing environments. Improvements in navigation accuracy and obstacle detection are accomplished by implementing adaptive pathplanning and integrating multiple sensors, guaranteeing the drone's efficient operation in real-life situations. The goal of this method is to enhance the drone's ability to make decisions, minimize human mistakes, and expand its range of potential uses in areas like surveillance, agriculture, and disaster response

Accident Prevention System for Cars, Buses, Trucks

Driver drowsiness is a significant factor in road accidents, contributing to a large number of crashes annually. To enhance road safety, the development of a Drivers Drowsiness Detection System is essential. This system builds to detect early signs of lazyness in drivers and provide timely alerts to prevent accidents. The proposed system uses to track key indicators of drowsiness, such as eye closure, head position, yawning, and blink rate. By utilizing a camera-based real-time monitoring system, it continuously analyzes the driver’s facial expressions. The system employs cadcade algorithms to distinguish a featurebased object detection algorithm to detect objects from images between alert and drowsy states based on collected data. When drowsiness is detected, the system triggers alerts like audio warnings, seat vibrations, or even vehicle slowing mechanisms, depending on the integration. This technology has the potential to significantly reduce the number of road accidents related to driver fatigue and could be applied in both personal vehicles and commercial fleets. The implementation of such systems represents a critical step toward improving road safety and decreasing driver-related incidents. Nowadays it is very challenging to stay active all the time due to busy schedules. Falling asleep while driving can lead to serious consequences, accidents, and even death. This situation is much more common and therefore it is very important to solve this problem. So, to solve this problem, we developed a sleep alarm system for drivers. This system alerts the user when he falls asleep at the wheel, thus the main concern is preventing accidents and saving lives. This system is useful for long- distance travelers and late-night drivers.

Evaluation of Automated Object-Detection Algorithms for Koala Detection in Infrared Aerial Imagery.

Effective detection techniques are important for wildlife monitoring and conservation applications and are especially helpful for species that live in complex environments, such as arboreal animals like koalas (Phascolarctos cinereus). The implementation of infrared cameras and drones has demonstrated encouraging outcomes, regardless of whether the detection was performed by human observers or automated algorithms. In the case of koala detection in eucalyptus plantations, there is a risk to spotters during forestry operations. In addition, fatigue and tedium associated with the difficult and repetitive task of checking every tree means automated detection options are particularly desirable. However, obtaining high detection rates with minimal false alarms remains a challenging task, particularly when there is low contrast between the animals and their surroundings. Koalas are also small and often partially or fully occluded by canopy, tree stems, or branches, or the background is highly complex. Biologically inspired vision systems are known for their superior ability in suppressing clutter and enhancing the contrast of dim objects of interest against their surroundings. This paper introduces a biologically inspired detection algorithm to locate koalas in eucalyptus plantations and evaluates its performance against ten other detection techniques, including both image processing and neural-network-based approaches. The nature of koala occlusion by canopy cover in these plantations was also examined using a combination of simulated and real data. The results show that the biologically inspired approach significantly outperformed the competing neural-network- and computer-vision-based approaches by over 27%. The analysis of simulated and real data shows that koala occlusion by tree stems and canopy can have a significant impact on the potential detection of koalas, with koalas being fully occluded in up to 40% of images in which koalas were known to be present. Our analysis shows the koala's heat signature is more likely to be occluded when it is close to the centre of the image (i.e., it is directly under a drone) and less likely to be occluded off the zenith. This has implications for flight considerations. This paper also describes a new accurate ground-truth dataset of aerial high-dynamic-range infrared imagery containing instances of koala heat signatures. This dataset is made publicly available to support the research community.

Traffic Sign Detection Using You Only Look Once (YOLOv3) Technique

Although deep learning-based object detection has produced excellent performance, there are still many issues with images from real-world capture, including rotating jitter, blurring, and noise deletion. The impact of these issues on object detection is significant. The main goal of this paper is to develop a real-time “You Only Look Once” (YOLOv3) algorithm to detect traffic signs. Compared to all other object detection algorithms, the YOLO method has a number of benefits. In contrast to different algorithms, YOLO looks at the image entirely by making predictions of the bounding boxes utilizing a convolutional neural network (CNN), determining the probability of each class for these boxes, and detecting the image more quickly. The proposed method applies a single neural network to the entire image. Then this network divides that image into regions, which provide the bounding boxes and also predict probabilities for each region. These generated bounding boxes are weighted by the predicted probabilities. The proposed method achieves 99% accuracy in the detection process.

WoodYOLO: A Novel Object Detector for Wood Species Detection in Microscopic Images

Wood species identification plays a crucial role in various industries, from ensuring the legality of timber products to advancing ecological conservation efforts. This paper introduces WoodYOLO, a novel object detection algorithm specifically designed for microscopic wood fiber analysis. Our approach adapts the YOLO architecture to address the challenges posed by large, high-resolution microscopy images and the need for high recall in localization of the cell type of interest (vessel elements). Our results show that WoodYOLO significantly outperforms state-of-the-art models, achieving performance gains of 12.9% and 6.5% in F2 score over YOLOv10 and YOLOv7, respectively. This improvement in automated wood cell type localization capabilities contributes to enhancing regulatory compliance, supporting sustainable forestry practices, and promoting biodiversity conservation efforts globally.

Avatar Detection in Metaverse Recordings

The metaverse is gradually expanding. There is a growing number of photo and video recordings of metaverse virtual worlds being used in multiple domains, and the collection of these recordings is a rapidly growing field. An essential element of the metaverse and its recordings is the concept of avatars. In this paper, we present the novel task of avatar detection in metaverse recordings, supporting semantic retrieval in collections of metaverse recordings and other use cases. Our work addresses the characterizations and definitions of avatars and presents a new model that supports avatar detection. The latest object detection algorithms are trained and tested on a variety of avatar types in metaverse recordings. Our work achieves a significantly higher level of accuracy than existing models, which encourages further research in this field.