Performance Of Object Detection Algorithms Research Articles

Optimizing Object Detection Algorithms for Congenital Heart Diseases in Echocardiography: Exploring Bounding Box Sizes and Data Augmentation Techniques.

Congenital heart diseases (CHDs), particularly atrial and ventricular septal defects, pose significant health risks and common challenges in detection via echocardiography. Doctors often employ the cardiac structural information during the diagnostic process. However, prior CHD research has not determined the influence of including cardiac structural information during the labeling process and the application of data augmentation techniques. This study utilizes advanced artificial intelligence (AI)-driven object detection frameworks, specifically You Look Only Once (YOLO)v5, YOLOv7, and YOLOv9, to assess the impact of including cardiac structural information and data augmentation techniques on the identification of septal defects in echocardiographic images. The experimental results reveal that different labeling strategies substantially affect the performance of the detection models. Notably, adjustments in bounding box dimensions and the inclusion of cardiac structural details in the annotations are key factors influencing the accuracy of the model. The application of deep learning techniques in echocardiography enhances the precision of detecting septal heart defects. This study confirms that careful annotation of imaging data is crucial for optimizing the performance of object detection algorithms in medical imaging. These findings suggest potential pathways for refining AI applications in diagnostic cardiology studies.

Object Detection System

Object detection is a critical component of computer vision, with significant applications across various domains. The challenges associated with real-world images, including noise, blurring, and rotational jitter, substantially impact the performance of object detection algorithms. YOLO (You Only Look Once), an algorithm grounded in convolutional neural networks, offers real-time object detection capabilities. This paper delves into several enhancements made to the YOLO network, aimed at augmenting the precision and efficiency of object detection tasks. The advancements discussed include optimizing the architecture of YOLO to handle diverse environmental conditions and integrating state-of-the-art techniques to mitigate common image distortions. Moreover, the paper explores the application of light field cameras to enhance depth perception and object localization. By refining the YOLO network, we aim to push the boundaries of real-time detection accuracy and reliability, crucial for applications ranging from autonomous vehicles to security surveillance systems.

PODB: A learning-based polarimetric object detection benchmark for road scenes in adverse weather conditions

Due to its insensitivity to light intensity and the capability to capture multidimensional information, polarimetric imaging technology has been proven to have advantages over traditional intensity-based imaging techniques for object detection tasks in adverse environmental conditions, particularly in road traffic scenarios. Recently, with the rapid development of artificial intelligence technology, deep learning (DL)-powered object detection techniques can further enhance recognition accuracy and algorithm robustness. This improvement is made possible by the ability of DL technology to leverage large datasets and extract deeper levels of target-specific features. However, constructing large-scale polarimetric datasets poses challenges as obtaining polarimetric information requires multiple captures of intensity images. In other words, the workload is several times higher compared to traditional imaging techniques. To address the current scarcity of polarimetric datasets and evaluate the practical performance of various algorithms on polarimetric datasets, this paper proposes a Polarimetric Object Detection Benchmark (PODB) dataset. The PODB provides an integrated quality evaluation framework for DL-based object detection algorithms in complex road scenes by incorporating polarimetric imaging. Besides, we conducted extensive object detection experiments using the PODB, which allowed for a comprehensive validation and performance evaluation of effective benchmark algorithms. Furthermore, a physics-based multi-scale image fusion cascaded object detection neural network model is proposed. By combining the multidimensional information provided by polarized images with an adaptive learning multi-decision object detection neural network model, the recognition accuracy of complex road scenes in adverse weather conditions has been improved by approximately 10%. Additionally, we anticipate that PODB will serve as an effective platform for evaluating and comparing the performance of object detection algorithms, as well as providing researchers with a baseline for future studies in developing new DL-based methods.

Synthetic Data Generation Based on RDB-CycleGAN for Industrial Object Detection

Deep learning-based methods have demonstrated remarkable success in object detection tasks when abundant training data are available. However, in the industrial domain, acquiring a sufficient amount of training data has been a challenge. Currently, many synthetic datasets are created using 3D modeling software, which can simulate real-world scenarios and objects but often cannot achieve complete accuracy and realism. In this paper, we propose a synthetic data generation framework for industrial object detection tasks based on image-to-image translation. To address the issue of low image quality that can arise during the image translation process, we have replaced the original feature extraction module with the Residual Dense Block (RDB) module. We employ the RDB-CycleGAN network to transform CAD models into realistic images. Additionally, we have introduced the SSIM loss function to strengthen the network constraints of the generator and conducted a quantitative analysis of the improved RDB-CycleGAN-generated synthetic data. To evaluate the effectiveness of our proposed method, the synthetic data we generate effectively enhance the performance of object detection algorithms on real images. Compared to using CAD models directly, synthetic data adapt better to real-world scenarios and improve the model’s generalization ability.

An Object Detection Method Based on Feature Uncertainty Domain Adaptation for Autonomous Driving

The environment perception algorithm in autonomous driving is trained in the source domain, leading to domain drift and reduced detection accuracy in the target domain due to shifts in background feature distribution. To address this issue, a domain adaptive object detection algorithm based on feature uncertainty is proposed, which can improve the detection performance of object detection algorithms in unlabeled data. Firstly, a local alignment module based on channel information is proposed, which can obtain the model’s uncertainty about different domain data based on the feature channels obtained through the feature extraction network, achieving adaptive dynamic local alignment. Secondly, an instance-level alignment module guided by local feature uncertainty is proposed, which can obtain the corresponding instance-level uncertainty through ROI mapping. To improve the domain invariance of bounding box regression, a multi-class, multi-regression instance-level uncertainty alignment module is proposed, which can achieve spatial decoupling of classification and regression tasks, further improving the model’s domain adaptive ability. Finally, the effectiveness of the proposed algorithm is validated on Cityscapes, KITTI, and real vehicle data.

SODA: A large-scale open site object detection dataset for deep learning in construction

Comprehensive image datasets can benefit the construction industry in terms of serving as the basis for generating deep-learning-based object detection models and testing the performance of object detection algorithms, but building such datasets is complex and requires vast professional knowledge. This paper develops and publicly releases a new large-scale image dataset specifically collected and annotated for the construction site, called Site Object Detection Dataset (SODA), which contains 15 object classes categorized by the worker, material, machine, and layout. >20,000 images were collected from multiple construction sites in different situations, weather conditions, and construction phases, covering different angles and perspectives. Statistical analysis shows that the dataset is well developed in terms of diversity and volume. Further evaluation with two widely-adopted deep learning-based object detection algorithms also illustrates the feasibility of the dataset, achieving a maximum mAP of 81.47%. This research contributes a large-scale open image dataset for the construction industry and sets up a performance benchmark for further evaluation of relevant algorithms.

Using Synthetic Images to Evaluate and Improve Object Detection Neural Network Performance on Aerial Image Datasets

Machine learning-based models for object detection heavily rely on large datasets of labeled images. When models trained on these datasets are applied to Unmanned Aerial Vehicle (UAV) imagery, the problem arises that the conditions under which the training images were created (lighting, altitude, angle) may be different to the UAVs applied conditions, leading to misclassifications. This problem becomes even more pressing in safety critical applications where failures can have huge negative impacts and constitute obstacles for certification of cognitive UAV components. Along a case study on car detection in low-altitude aerial imagery, we show that using, both, artificial and real images for model training has a positive effect on the performance of object detection algorithms when the trained model is applied on images from another domain. Additionally, we show that weak points from object detection neural networks trained on real-world images transfer to synthetic images and that synthetic data can be used to evaluate neural networks trained on real-world data. Since simulated images are easy to create and object labels are inherently given, the presented approaches show a promising direction for scenarios where adequate datasets are difficult to obtain, as well as for the targeted exploration of weak points of object detection algorithms.

Performance of a modified YOLOv3 object detector on remotely piloted aircraft system acquired full motion video

Remotely piloted aircraft systems (RPAS) have introduced a new ability to quickly deploy low-cost, fully or partially autonomous aerial sensor platforms, which has created new intelligence, surveillance, and reconnaissance capabilities in various domains using cameras that are ubiquitous in most RPAS. The mounted cameras acquire images or full-motion video (FMV) which can be analyzed using object detection algorithms for locating and classifying one or more specified targets. To date, there has not been much published work regarding the effect of the RPAS flight parameters on the performance of object detection algorithms. To explore the use of object detection on aerial FMV acquired at various RPAS flight parameter settings, a dataset acquisition campaign was launched resulting in 8.5 h of RPAS-acquired FMV. Analysis and interpretation of the acquired dataset revealed that state-of-the-art performance was achieved using a modified you only look once object detection algorithm when the RPAS was deployed under an altitude of 30 m, at a velocity of under 7 m/s, and at pitch angles ranging from 25 deg to 65 deg while acquiring FMV at a resolution of 4.16 MP. The experimental results show that, when flown under specific conditions, RPAS are an effective and reliable platform for acquiring aerial FMV for the purpose of object detection which has a variety of different applications, such as peace support, public safety, and aerial monitoring.

An improved object detection algorithm based on YOLO*

Accuracy and speed have always been a measure of the performance of object detection algorithms. The current algorithms have reduced the detection speed on the basis of increasing a certain accuracy due to their complex structure. In response to this problem, this paper uses the RepVGG network to improve the original YOLOv3 structure, which uses a diversified branch structure to enhance the network feature extraction ability during training and transforms the training model into an equivalent VGG-like topology network model during inference. In addition, we use ASFF to deal with the problem of mutually restricted scales. Experiments show that compared with the original algorithm, the improved algorithm increases mAP by 0.51 on the VOC data set, and at the same time the speed increases by 10%.

Object Detection Enhancement Algorithm Based on Curriculum Learning

<p indent=0mm>The performance of object detection algorithms depends on both dataset distribution and network design of feature extraction. Starting from these two points, we firstly explore the potential inherent reasons that lead to low detection accuracy of small object by analyzing the distribution of object attributes at various scales in the COCO 2017 dataset, and propose copy and paste (CP) module accordingly, which adjusts the distribution of small object offline, on the one hand, upsampling the pictures containing small objects, on the other hand, copying and pasting the small objects in the pictures. Then, to further improve network feature extraction ability, inspired by the idea of curriculum learning (CL), we propose CL layer, which uses ground truth labels to guide the learning process, and CL factor to control the learning intensity, the features of objects are enhanced to facilitate network feature extraction. We deploy the CP module on the COCO 2017 dataset and embed the CL layer in the CenterNet network to conduct multiple sets of comparative experiments, and use average detection accuracy, small object detection accuracy, medium object detection accuracy, and large object detection accuracy as evaluation indicators. The experimental results prove the effectiveness of CP module and CL layer.

Object detection mechanism based on deep learning algorithm using embedded IoT devices for smart home appliances control in CoT

Object detection and recognition is commonly used in diverse computer vision based applications and many algorithms are proposed in literature. However, application of object detection algorithms in real-time systems demand minimal computation time and comprehensive performance analysis needs to be conducted before deployment. This paper aims to conduct performance analysis of deep learning based algorithm i.e. single shot detector (SSD) in IoT based embedded devices for smart home appliances control. We have developed a smart home automation system using object detection algorithm based on model view controller (MVC) architecture deployed on Cloud of Things (CoT) i.e. Amazon Web Service (AWS) cloud for users to remotely monitor their homes. Message queuing telemetry transport (MQTT) protocol is used for communication with connected IoT devices. For load-balancing, we have proposed the concept of distributed broker to support high number of publishers and subscribers. For experimental analysis, we have connected a camera with Raspberry Pi for object detection based on deep learning algorithm (SSD) using OpenCV library in our proposed system. Experiments are conducted to evaluate the performance of object detection algorithm under varying environmental conditions by changing the light intensity level, distance of object from camera, and frame size of video. Results show that communication delay is very low (i.e. 0.2 s) as compared to processing delay in Raspberry Pi. Furthermore, changing environmental conditions have very low/insignificant impact on the processing delay of object detection algorithm i.e. average delay of 1.7 s (stdev. 0.18) and 1.8 s (stdev. 0.24) in bright and dark lighting levels, respectively. However, accuracy is deteriorated under low lighting intensity level and increased frame sizes i.e. from 95–100 to 80–85%. Selected embedded device, camera model and object detection algorithm limits the performance of object detection in real-time systems and shall be carefully selected to fulfill the requirement.

Occlusion Problem-Oriented Adversarial Faster-RCNN Scheme

In the practical scene, object detection faces a very complicated situation. The occlusion problem always occurs in actual scene, which may affect the accuracy of object detection, especially for the occluded objects. For the deep models, a larger dataset with sufficient occlusion samples will improve the performance of the object detection models. However, the sample with occlusion problem is too hard to obtain. Therefore, a global average pooling(GAP) based adversarial Faster-RCNN is proposed to generate the hard samples and enhance the performance of object detection algorithm. Sufficient hard samples can be generated with the help of this model. Therefore, the object detection model can be trained adequately for the occluded objects. The hard sample generation is carried out in the space of image feature instead of image generation directly. The class-dependent part is obtained by the GAP network, and it is obscured to generate the feature map of hard sample for model reinforcement training. Therefore, the better object detection model can be trained using a conventional dataset. The Faster-RCNN is adopted as the baseline. The Faster-RCNN and GAP have a joint training to improve the performance of the proposed model. The simulation results exhibit the validation of the proposed algorithm.

A Review on the Performance of Object Detection Algorithm

This paper represents multiple Object recognitions technology in the field of computer vision for finding and identifying multiple objects in a image or video sequence.It is basically highlight only those objects which are needed. Algorithmic descriptions of recognition task are implemented on machines which is an complex job. Thus multiple object recognition techniques need to be developed which are less intricate and well-organized The multiple object detection is a very important application of image processing. the literature survey has shown that the most of existing methods have ignored the poor quality images like image with noise or poor intensity . Noise means those signals which are not required .Also the most of the existing work for multiple object detection has neglected the use of hybrid technique. The overall goal of this research work is to propose an efficient and simple multiple object detection using the fuzzy and transition region based image segmentation

Performance evaluation of object detection algorithms for video surveillance

In this paper, we propose novel methods to evaluate the performance of object detection algorithms in video sequences. This procedure allows us to highlight characteristics (e.g., region splitting or merging) which are specific of the method being used. The proposed framework compares the output of the algorithm with the ground truth and measures the differences according to objective metrics. In this way it is possible to perform a fair comparison among different methods, evaluating their strengths and weaknesses and allowing the user to perform a reliable choice of the best method for a specific application. We apply this methodology to segmentation algorithms recently proposed and describe their performance. These methods were evaluated in order to assess how well they can detect moving regions in an outdoor scene in fixed-camera situations