Federated Object Detection

Sea turtles exhibit high migratory rates and occupy a broad range of habitats, which in turn makes monitoring these taxa challenging. Applying deep learning (DL) models to vast image datasets collected from citizen science programs can offer promising solutions to overcome the challenge of monitoring the wide habitats of wildlife, particularly sea turtles. Among DL models, object detection models, such as the You Only Look Once (YOLO) series, have been extensively employed for wildlife classification. Despite their successful application in this domain, detecting objects in images with complex backgrounds, including underwater environments, remains a significant challenge. Recently, instance segmentation models have been developed to address this issue by providing more accurate classification of complex images compared to traditional object detection models. This study compared the performance of two state-of-the-art DL methods namely; the object detection model (YOLOv5) and instance segmentation model (YOLOv5-seg), to detect and classify sea turtles. The images were collected from iNaturalist and Google and then divided into 64% for training, 16% for validation, and 20% for test sets. Model performance during and after finishing training was evaluated by loss functions and various indexes, respectively. Based on loss functions, YOLOv5-seg demonstrated a lower error rate in detecting rather than classifying sea turtles than the YOLOv5. According to mean Average Precision (mAP) values, which reflect precision and recall, the YOLOv5-seg model showed superior performance than YOLOv5. The mAP0.5 and mAP0.5:0.95 for the YOLOv5 model were 0.885 and 0.795, respectively, whereas for the YOLOv5-seg, these values were 0.918 and 0.831, respectively. In particular, based on the loss functions and classification results, the YOLOv5-seg showed improved performance for detecting rather than classifying sea turtles compared to the YOLOv5. The results of this study may help improve sea turtle monitoring in the future.

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.

Comprehensive study on the development of an automatic helmet violator detection system (AHVDS) using advanced machine learning techniques

Crop disease detection in the actual field is difficult due to the unstructured environment. The images taken from the farms are covered mainly by green-colored plants or leaves, from which slightly varied portions of diseases are highly challenging to identify, even with the naked eye. This study contributes to detect the chilli leaf disease from images collected from actual field conditions. An RGB camera was used to collect images for the dataset from a chilli field. The research utilized one of the state-of-the-art deep learning object detection models named YOLOv5. The model is very efficient considering its speed of detection and accuracy. The model performed well despite having a small dataset with a mean average precision (mAP) of 0.461. The proposed deep learning object detection model is appreciably promising for disease detection of chilli crop.

With the development of industrial automation, the importance of mechanical parts in the production process is becoming increasingly important. In recent years, deep learning technology has made breakthrough progress in fields such as image recognition and object detection. Deep learning models can learn a large amount of data through multiple epochs, automatically extract features from it, and achieve image recognition and object detection. This provides potent technical assistance for the design of mechanical component recognition systems. In industrial production, there are a wide variety of mechanical parts with complex shapes, and the differences between different models are often very small, making it difficult to identify them manually. Therefore, it is necessary to develop a system that can automatically identify mechanical parts to improve production efficiency and quality. This article takes mechanical parts as the research object and studies the recognition technology of mechanical parts based on deep learning and image recognition. The main content of the article includes the following aspects. Research was conducted on image quality enhancement methods for images with different characteristics, and different image preprocessing methods were applied to different images. YOLOv5 and SSD (Single Shot MultiBox Detector) algorithms are used to perform deep learning and recognition detection on the processed images, respectively. By comprehensively comparing the differences between the two algorithms, YOLOv5 was selected as the focus of this design, and based on this, deep training was conducted, and the code was imported into the embedded system.

The 2021 embedded deep learning object detection model compression competition for traffic in Asian countries held in IEEE ICMR2021 Grand Challenges focuses on the object detection technologies in autonomous driving scenarios. The competition aims to detect objects in traffic with low complexity and small model size in the Asia countries (e.g., Taiwan), which contains several harsh driving environments. The target detected objects include vehicles, pedestrians, bicycles and crowded scooters. There are 89,002 annotated images provided for model training and 1,000 images for validation. Additional 5,400 testing images are used in the contest evaluation process, in which 2,700 of them are used in the qualification stage competition, and the rest are used in the final stage competition. There are in total 308 registered teams joining this competition this year, and the top 15 teams with the highest detection accuracy entering the final stage competition, from which 9 teams submitted the final results. The overall best model belongs to team "as798792", followed by team "Deep Learner" and team "UCBH." Two special awards of best accuracy award best and bicycle detections go to the same team "as798792," and the other special award of scooter detection goes to team "abcda."

The historical Lingnan gray brick buildings in Macau, a World Heritage Site, are facing severe deterioration due to prolonged disrepair, manifesting as cracks, breakages, moss adhesion, and other types of surface damage. These issues threaten not only the structural stability of the buildings but also the conservation of cultural heritage. To address the inefficiencies and low accuracy of traditional manual inspections, this study proposes an automated recognition and quantitative detection method for wall surface damage based on the YOLOv8 deep learning object detection model. A dataset comprising 375 annotated images collected from 162 gray brick historical buildings in Macau was constructed, covering eight damage categories: crack, damage, missing, vandalism, moss, stain, plant, and intact. The model was trained and validated using a stratified sampling approach to maintain a balanced class distribution, and its performance was comprehensively evaluated through metrics such as the mean average precision (mAP), F1 score, and confusion matrices. The results indicate that the best-performing model (Model 3 at the 297th epoch) achieved a mAP of 61.51% and an F1 score up to 0.74 on the test set, with superior detection accuracy and stability. Heatmap analysis demonstrated the model’s ability to accurately focus on damaged regions in close-range images, while damage quantification tests showed high consistency with manual assessments, confirming the model’s practical viability. Furthermore, a portable, integrated device embedding the trained YOLOv8 model was developed and successfully deployed in real-world scenarios, enabling real-time damage detection and reporting. This study highlights the potential of deep learning technology for enhancing the efficiency and reliability of architectural heritage protection and provides a foundation for future research involving larger datasets and more refined classification strategies.

The indoor scene object detection technology is of important research significance, which is one of the popular research topics in the field of scene understanding for indoor robots. In recent years, the solutions based on deep learning have achieved good results in object detection. However, there are still some problems to be further studied in indoor object detection methods, such as lighting problem and occlusion problem caused by the complexity of the indoor environment. Aiming at these problems, an improved object detection method based on deep neural networks is proposed in this article, which uses a framework similar to the single-shot multibox detector (SSD). In the proposed method, an improved ResNet50 network is used to enhance the transmission of information, and the feature expression capability of the feature extraction network is improved. At the same time, a multiscale contextual information extraction (MCIE) module is used to extract the contextual information of the indoor scene, so as to improve the indoor object detection effect. In addition, an improved dual-threshold non-maximum suppression (DT-NMS) algorithm is used to alleviate the occlusion problem in indoor scenes. Finally, the public dataset SUN2012 is further screened for the special application of indoor scene object detection, and the proposed method is tested on this dataset. The experimental results show that the mean average precision (mAP) of the proposed method can reach 54.10%, which is higher than those of the state-of-the-art methods.

Deep learning techniques have recently demonstrated remarkable success in numerous domains. Typically, the success of these deep learning models is measured in terms of performance metrics such as accuracy and mean average precision (mAP). Generally, a model's high performance is highly valued, but it frequently comes at the expense of substantial energy costs and carbon footprint emissions during the model building step. Massive emission of CO2 has a deleterious impact on life on earth in general and is a serious ethical concern that is largely ignored in deep learning research. In this article, we mainly focus on environmental costs and the means of mitigating carbon footprints in deep learning models, with a particular focus on models created using knowledge distillation (KD). Deep learning models typically contain a large number of parameters, resulting in a 'heavy' model. A heavy model scores high on performance metrics but is incompatible with mobile and edge computing devices. Model compression techniques such as knowledge distillation enable the creation of lightweight, deployable models for these low-resource devices. KD generates lighter models and typically performs with slightly less accuracy than the heavier teacher model (model accuracy by the teacher model on CIFAR 10, CIFAR 100, and TinyImageNet is 95.04%, 76.03%, and 63.39%; model accuracy by KD is 91.78%, 69.7%, and 60.49%). Although the distillation process makes models deployable on low-resource devices, they were found to consume an exorbitant amount of energy and have a substantial carbon footprint (15.8, 17.9, and 13.5 times more carbon compared to the corresponding teacher model). The enormous environmental cost is primarily attributable to the tuning of the hyperparameter, Temperature (τ). In this article, we propose measuring the environmental costs of deep learning work (in terms of GFLOPS in millions, energy consumption in kWh, and CO2 equivalent in grams). In order to create lightweight models with low environmental costs, we propose a straightforward yet effective method for selecting a hyperparameter (τ) using a stochastic approach for each training batch fed into the models. We applied knowledge distillation (including its data-free variant) to problems involving image classification and object detection. To evaluate the robustness of our method, we ran experiments on various datasets (CIFAR 10, CIFAR 100, Tiny ImageNet, and PASCAL VOC) and models (ResNet18, MobileNetV2, Wrn-40-2). Our novel approach reduces the environmental costs by a large margin by eliminating the requirement of expensive hyperparameter tuning without sacrificing performance. Empirical results on the CIFAR 10 dataset show that the stochastic technique achieves an accuracy of 91.67%, whereas tuning achieves an accuracy of 91.78%-however, the stochastic approach reduces the energy consumption and CO2 equivalent each by a factor of 19. Similar results have been obtained with CIFAR 100 and TinyImageNet dataset. This pattern is also observed in object detection classification on the PASCAL VOC dataset, where the tuning technique performs similarly to the stochastic technique, with a difference of 0.03% mAP favoring the stochastic technique while reducing the energy consumptions and CO2 emission each by a factor of 18.5.

Object detection plays a crucial role in computer vision applications, ranging from autonomous vehicles to surveillance systems. One-stage object detectors have emerged as a powerful solution by simplifying detection pipelines, enabling real-time performance while maintaining competitive accuracy. This article provides a comprehensive survey of one-stage obj ect detection models, including you only look once (YOLO), single shot multibox detector (SSD), and PaddlePaddle YOLO (PP-YOLO) variants. A central question guides this exploration: How can incremental architectural refinements and training strategies improve the trade-off between speed, accuracy, and computational efficiency in object detection models for real-time applications? Through a detailed analysis of key innovations, performance metrics, and practical applications, this survey highlights the evolution of these models and their contributions to bridging the gap between research and deployment. Additionally, the paper identifies current challenges, such as small-object detection and resource efficiency, and proposes future research directions to advance the field further.

Foreign bodies such as a surgical gauze can be retained in the body after surgery and in some cases cannot be detected by postoperative radiography. The aim of this study was to develop an object detection model capable of postsurgical detection of retained gauze in the body. The object detection model used deep learning using abdominal radiographs, and a phantom study was performed to evaluate the ability of the model to automatically detect retained surgical gauze. The object detection model was constructed using a Single Shot MultiBox Detector (SSD) 300. In total, 268 abdominal phantom images were used: 180 gauze images were used as training data, 20 gauze images were used as validation data, and an additional 34 gauze images and 34 nongauze images were used as test data. To evaluate the performance of the object detection model, a confusion matrix was created and the accuracy and sensitivity were calculated. True-positive (TP) rate, true-negative (TN) rate, false-positive (FP) rate, and false-negative (FN) rate were 0.92, 1.00, 0.00, and 0.08, respectively. Accuracy was 0.96, and sensitivity was 0.92. The object detection model could detect surgical gauze on abdominal phantom images with a high accuracy and sensitivity.

Pipeline magnetic flux leakage (MFL) detection technology has been widely used in online pipeline defect detection due to its advantages of not requiring coupling agents and being easily automated. Accurately predicting defect sizes based on detection data and conducting applicability evaluations are crucial for subsequent repair decisions. Based on the collected MFL data, a deep learning object detection model based on PP-YOLOE (Paddle Paddle - You Only Look Once Evolved) is proposed according to the characteristics of defect data. By converting MFL data into images and feeding them into the model for object detection training, defects can be quickly located and data extracted, providing an accurate and reliable dataset for defect quantification. The axial and radial MFL data of pipeline defects are used as inputs to the model, and the length, width, and depth of defects are output in parallel according to the characteristics of MFL data, thus achieving the assessment and prediction of defect sizes.

An automatic inspection system for pest detection in granaries using YOLOv4

The detection of rotated objects is a meaningful and challenging research work. Although the state-of-the-art deep learning models have feature invariance, especially convolutional neural networks (CNNs), their architectures did not specifically design for rotation invariance. They only slightly compensate for this feature through pooling layers. In this study, we propose a novel network, named LPNet, to solve the problem of object rotation. LPNet improves the detection accuracy by combining retina-like log-polar transformation. Furthermore, LPNet is a plug-and-play architecture for object detection and recognition. It consists of two parts, which we name as encoder and decoder. An encoder extracts images which feature in log-polar coordinates while a decoder eliminates image noise in cartesian coordinates. Moreover, according to the movement of center points, LPNet has stable and sliding modes. LPNet takes the single-shot multibox detector (SSD) network as the baseline network and the visual geometry group (VGG16) as the feature extraction backbone network. The experiment results show that, compared with conventional SSD networks, the mean average precision (mAP) of LPNet increased by 3.4% for regular objects and by 17.6% for rotated objects.

Object localization and detection is the emerging area of computer vision and image processing that finds out the location of the object in the video frames or in the digital images. Object localization and detection have many challenges like occlusion, scale variations, intraclass similarities, illumination conditions, pose variations, etc. Multi-view object detection focuses on different views of objects like the top, bottom, side view, etc. We aim to discuss the different Object detection models based on Machine learning and Deep neural network approaches in a multi-view environment. We also discuss different datasets used for object detections and their applications. We apply some object detection models like SSD and Faster R-CNN to specific object categories of Open Image Dataset V6 and compare the results based on mAP (Mean Average Precision).KeywordsObject detectionConvolution neural networksR-CNNFast R-CNNFaster R-CNNEfficientDetCenterNet