Common Objects In Context Dataset Research Articles

Foreign Object Debris Detection on Wireless Electric Vehicle Charging Pad Using Machine Learning Approach

Foreign object debris (FOD) includes any unwanted and unintentional material lying on the charging lane or parking lots, posing a risk to the wireless charging system, the vehicle, or the people inside. FOD in an Electric Vehicle (EV) wireless charging system can cause problems, including decreased charging efficiency, safety risks, charging system damage, communication issues, and health risks. To address this problem, this paper proposes the deep learning object detection network approach of using YOLOv4 (You Only Look Once), which is a single-shot detector. Additionally, for real-time implementation, YOLOv4-Tiny is suggested, which is a compressed version of YOLOv4 designed for devices with low computational power. YOLOv4-Tiny enables faster inferences and facilitates the deployment of FOD detectors on edge devices. The algorithm is trained using the FOD dataset, consisting of images of common debris on runways or taxiways. Furthermore, utilizing the concept of transfer learning, the last few layers of the pre-trained YOLOv4 model are modified using the COCO (Common Objects in Context) dataset to transfer features to the new network and retrain the model on the FOD dataset. The results obtained using this YOLOv4 model yielded a precision rate of 99.05%, while the results from YOLOv4-Tiny achieved a precision rate of 97.74%, with an average inference time of 150 ms under the ambient light and weather conditions.

Application of Machine Vision Techniques in Low-Cost Devices to Improve Efficiency in Precision Farming

In the context of recent technological advancements driven by distributed work and open-source resources, computer vision stands out as an innovative force, transforming how machines interact with and comprehend the visual world around us. This work conceives, designs, implements, and operates a computer vision and artificial intelligence method for object detection with integrated depth estimation. With applications ranging from autonomous fruit-harvesting systems to phenotyping tasks, the proposed Depth Object Detector (DOD) is trained and evaluated using the Microsoft Common Objects in Context dataset and the MinneApple dataset for object and fruit detection, respectively. The DOD is benchmarked against current state-of-the-art models. The results demonstrate the proposed method’s efficiency for operation on embedded systems, with a favorable balance between accuracy and speed, making it well suited for real-time applications on edge devices in the context of the Internet of things.

Sustainable Waste Management through ML-based Real-Time Trash Bin Prediction

Waste management has been an issue due to low awareness among people of any country to lead major environmental contamination, tragic accidents, and unfavorable working conditions for landfill workers. The Lack of precise and efficient object detection could be a barrier in the growth of computer vision-based systems. As per the latest research articles, pre-trained models could be used for Trash Bin detection in real time and for recommending appropriate actions after detection. Using a unique validation dataset made up of predicted trash items, the two classes of acceptable object identification models, YOLO (You Only Look Once) and SSD (Single Shot Multibox Detector), are then contrasted. It is concluded that SSD performs noticeably better than YOLO in identifying trash objects based on several performance metrics computed utilizing multiple open-source research projects. The model is then built up to recognize several trash object types after being pre-trained using Microsoft's COCO (Common Objects in Context) dataset. Our initiative intends to enhance sustainable waste management, make trash sorting incredibly simple, and guard against serious illnesses and accidents at landfill and garbage disposal sites.

CVII: Enhancing Interpretability in Intelligent Sensor Systems via Computer Vision Interpretability Index.

In the realm of intelligent sensor systems, the dependence on Artificial Intelligence (AI) applications has heightened the importance of interpretability. This is particularly critical for opaque models such as Deep Neural Networks (DNN), as understanding their decisions is essential, not only for ethical and regulatory compliance, but also for fostering trust in AI-driven outcomes. This paper introduces the novel concept of a Computer Vision Interpretability Index (CVII). The CVII framework is designed to emulate human cognitive processes, specifically in tasks related to vision. It addresses the intricate challenge of quantifying interpretability, a task that is inherently subjective and varies across domains. The CVII is rigorously evaluated using a range of computer vision models applied to the COCO (Common Objects in Context) dataset, a widely recognized benchmark in the field. The findings established a robust correlation between image interpretability, model selection, and CVII scores. This research makes a substantial contribution to enhancing interpretability for human comprehension, as well as within intelligent sensor applications. By promoting transparency and reliability in AI-driven decision-making, the CVII framework empowers its stakeholders to effectively harness the full potential of AI technologies.

110 Evaluation of Computer Vision to Analyze Beef Cattle Feeding Behavior

Abstract Leveraging computer vision (CV) methods to study pen-fed cattle feeding behavior presents several advantages, including monitoring animal health and identifying feed efficient animals. This research employed a region-based convolutional neural network (RCNN) combined with the common objects in context (COCO) dataset for automatic livestock recognition using CV techniques in experimental feedlot pens. Thirty Angus-influenced steers were allocated in one pen with four automated feed intake systems (AFIS; Vytelle SENSE). CV data were recorded during daylight hours using a webcam (Microsoft LifeCam Cinema) with a resolution of 1280x720 pixels at ten frames per second connected to a video surveillance camera software (Contaware, Switzerland). The CV dataset obtained by the cameras, Figure 1, was benchmarked with feeding behavior data obtained from observed annotations (OA) and AFIS. The CV model utilized was a Mask-RCNN with pre-trained weights on the COCO dataset. The Mask RCNN algorithm can identify and locate multiple objects, objects of different scales, and overlapping objects within an image. The COCO dataset is a large and diverse set of annotated images that can be used for training and evaluating object detection models. The fully trained Mask-RCNN model takes each video frame as input and outputs the pixel segmentation of each object detected. For the CV analyses, each animal bounding box was associated with a score threshold, and each pixel within was assigned a probability threshold; both ranging from 0 to 100. The higher the score and probability thresholds are, the fewer the boxes and pixels will be marked as the animal boxing shape, resulting in less feeding detection from the CV system. In contrast, a low score and probability thresholds produce many predictions, including false detections, which might be misleading. Therefore, a dataset analysis was conducted to optimize the best threshold combination. We evaluated the accuracy and precision of the CV model compared with OA and AFIS by analyzing a dataset section of feeding events of one feed bunk using a 0.5 score and 0.5 probability thresholds. We obtained the values for the true positive (TP), false positive (FP), true negative (TN), and false negative (FN) to calculate the accuracy = [TP+TN]/[TP+TN+FP+FN], and precision = [TP]/[TP+FP], Table 1. As a result, the CV model achieved 95.39% and 99.82% accuracy and 93.60% and 99.90% precision when compared with OA and AFIS, respectively. Our findings showcase the promising capabilities of employing the Mask-RCNN algorithm and COCO datasets for detecting beef cattle feeding behavior in feedlot pens. This approach holds significant value for the cattle industry by enabling precise monitoring and analysis of individual animal behavior within feedlot pens, facilitating early detection of behavioral abnormalities.

A New Perspective for Mining COCO Dataset

Microsoft Common Objects in Context (COCO) is a huge image dataset that has over 300 k images belonging to more than ninety-one classes. COCO has valuable information in the field of detection, segmentation, classification, and tagging; but the COCO dataset suffers from being unorganized, and classes in COCO interfere with each other. Dealing with it gives very low and unsatisfying results whether when calculating accuracy or intersection over the union in classification and segmentation algorithms. A simple method is proposed to create a customized subset from the COCO dataset by determining the class or class numbers. The suggested method is very useful as preprocessing step for any detection or segmentation algorithms such as YOLO, SSPNET, RCNN, etc. The proposed method was validated using the link net architecture for semantic segmentation. The results after applying the preprocessing were presented and compared to the state of art methods. The comparison demonstrates the exceptional effectiveness of transfer learning with our preprocessing model. Index Terms— COCO JSON files, Object detection, object tracking, semantic segmentation.

Transforming Healthcare: Leveraging Vision-Based Neural Networks for Smart Home Patient Monitoring

Image captioning is a promising technique for remote monitoring of patient behavior, enabling healthcare providers to identify changes in patient routines and conditions. In this study, we explore the use of transformer neural networks for image caption generation from surveillance camera footage, captured at regular intervals of one minute. Our goal is to develop and evaluate a transformer neural network model, trained and tested on the COCO (common objects in context) dataset, for generating captions that describe patient behavior. Furthermore, we will compare our proposed approach with a traditional convolutional neural network (CNN) method to highlight the prominence of our proposed approach. Our findings demonstrate the potential of transformer neural networks in generating natural language descriptions of patient behavior, which can provide valuable insights for healthcare providers. The use of such technology can allow for more efficient monitoring of patients, enabling timely interventions when necessary. Moreover, our study highlights the potential of transformer neural networks in identifying patterns and trends in patient behavior over time, which can aid in developing personalized healthcare plans.

Accurate and Efficient Federated-Learning-Based Edge Intelligence for Effective Video Analysis

Video data is the biggest IoT data which is challenging for effective analysis with good performance. Object mis-detection is usually inevitable in edge-based distributed cross-scene video analysis. Traditional centralized model training can potentially result in edge data leakage. Even though joint model can be trained with federated learning while maintaining data privacy, the size of gradient data transmitted is large for computer vision models used. To address these problems, this paper proposed an Accurate and efficient federated learning-based edge intelligence for effective video analysis method called EIEVA-AEFL. In EIEVA-AEFL, a Federation Mis-detection Reinforcement Network (FMRN) is designed to alleviate the mis-detection problem. FMRN contains a vanilla object detection network and a mis-detection reinforcement branch, which finetunes object detection via feature re-extraction to reduce object mis-detection. To reduce the communication cost in training, an efficient federated learning strategy is designed. In this strategy, an oscillation suppression loss function is proposed to suppress the loss fluctuation resulting from data on edge clients. Average accuracy and recall increase 0.5 and 0.7 with FMRN on the MS COCO (Microsoft Common Objects in Context) data set respectively, and with improvements of 4.5 and 5.5 with FMRN on our self-made mis-detection dataset respectively. EIEVA-AEFL can reduce the training speed on the premise of ensuring the accuracy of the model. The model parameters, data amount, transmission delay and convergence epochs on EIEVA-AEFL model training are reduced by 78%, 89%, 84% and 36% respectively.

A new YOLO-based method for social distancing from real-time videos.

The coronavirus disease (COVID-19) is primarily disseminated through physical contact. As a precaution, it is recommended that indoor spaces have a limited number of people and at least one meter apart. This study proposes a real-time method for monitoring physical distancing compliance in indoor spaces using computer vision and deep learning techniques. The proposed method utilizes YOLO (You Only Look Once), a popular convolutional neural network-based object detection model, pre-trained on the Microsoft COCO (Common Objects in Context) dataset to detect persons and estimate their physical distance in real time. The effectiveness of the proposed method was assessed using metrics including accuracy rate, frame per second (FPS), and mean average precision (mAP). The results show that the YOLO v3 model had the most remarkable accuracy (87.07%) and mAP (89.91%). On the other hand, the highest fps rate of up to 18.71 was achieved by the YOLO v5s model. The results demonstrate the potential of the proposed method for effectively monitoring physical distancing compliance in indoor spaces, providing valuable insights for future use in other public health scenarios.

NAS-FPNLite object detection method fused with cross stage connection and inverted residual

NAS-FPNLite object detection method fused with cross stage connection and inverted residual

Generating Human-Like Descriptions for the Given Image Using Deep Learning

One of the most prominent applications in the field of computer vision and natural language processing research is image captioner. The paper includes an exhaustive review of the literature on image captioning and the implementation using attention-based encoder-decoder model. The process of depicting an image with textual explanations is known as image captioning. The problem has seen extensive use of encoder-decoder frameworks. In this study, Deep Convolutional Neural Network (CNN) for image classification and Recurrent Neural Network (RNN) for sequence modeling are combined to build a single network that creates descriptions of images using the Microsoft Common Objects in Context Dataset (MSCOCO Dataset). Because of RNNs being computationally expensive to train and assess, memory is often restricted to a few items. By highlighting the most important components of an input image, the Attention model had been used to address this issue. The model was developed using Nvidia Quadro RTX5000 GPU (CUDA), which received the Bleu-1 score of 0.5793 for the 100 generated sentences. The captions generated by the model on the testing dataset labeled nearly all of the objects in the image and were sufficiently like the actual captions in the annotations, even on images outside of the testing dataset.

Deep learning detection network for peripheral blood leukocytes based on improved detection transformer

Leukocytes serve as an important barrier to healthy immunity in the body and play an important role in fighting diseases. Manual morphological examination of leukocytes is the gold standard for the diagnosis of certain diseases but is undoubtedly labour-intensive and requires a high level of expertise. Therefore, conducting research on computer-aided diagnostics is important. With the development of deep learning techniques in computer vision, an increasing number of deep learning-based methods are now being applied in the field of medical imaging. Recently, the detection transformer (DETR) model, which is based on the transformer architecture, has exhibited outstanding performances in object detection tasks and has attracted considerable attention. Our study aims to propose a pure transformer-based end-to-end object detection network based on DETR and apply it to a practical medical scenario of leukocyte detection. First, we introduce the pyramid vision transformer and deformable attention module into the DETR model to improve the model performance and convergence speed. Second, we train the improved model on the challenging Common Objects in Context dataset to obtain the pretrained weights. Third, we perform transfer learning on the modified Raabin leukocyte dataset to obtain the optimal model. The improved DETR shows a mean average precision detection performance of up to 0.961 and is therefore superior to the original DETR and convolutional neural network. The study findings are expected to be useful for the development of a transformer structural model for leukocyte detection.

MLA-Net: Feature Pyramid Network with Multi-Level Local Attention for Object Detection

Feature pyramid networks and attention mechanisms are the mainstream methods to improve the detection performance of many current models. However, when they are learned jointly, there is a lack of information association between multi-level features. Therefore, this paper proposes a feature pyramid of the multi-level local attention method, dubbed as MLA-Net (Feature Pyramid Network with Multi-Level Local Attention for Object Detection), which aims to establish a correlation mechanism for multi-level local information. First, the original multi-level features are deformed and rectified using the local pixel-rectification module, and global semantic enhancement is achieved through the multi-level spatial-attention module. After that, the original features are further fused through the residual connection to achieve the fusion of contextual features to enhance the feature representation. Extensive ablation experiments were conducted on the MS COCO (Microsoft Common Objects in Context) dataset, and the results demonstrate the effectiveness of the proposed method with a 0.5% enhancement. An improvement of 1.2% was obtained on the PASCAL VOC (Pattern Analysis Statistical Modelling and Computational Learning, Visual Object Classes) dataset, reaching 81.8%, thereby, indicating that the proposed method is robust and can compete with other advanced detection models.

Multistage attention network for human pose estimation

Human pose estimation is a fundamental yet challenging task in computer vision. Although many methods have achieved significant improvement, they are still insufficient for the fusion of feature maps at different stages, such as the stacked hourglass network (SHNet). The SHNet is a classic human pose estimation network that extracts multiscale features through stacked multistage downsampling and upsampling operations. We propose a multistage attention mechanism to fuse the multistage feature maps. Furthermore, we apply it in the SHNet to propose a multistage attention network (MANet). In the experiments, we demonstrated the effectiveness of MANet in human pose estimation on the common objects in context dataset and the MPII human pose dataset.

Using bilateral filtering and autoencoder to defend against adversarial attacks for object detection

With the development of adversarial attacks, the performance of object detection based on deep learning is threatened. When adversarial examples are introduced into the detection task, the detector will suffer from poor detection performance, causing a large number of false detections. To handle this problem, we propose a defense method by combing bilateral filtering and the denoising autoencoder. Taking the you only look once (YOLO) v4 detection model as the research target, the proposed method proceeds as follows. First, it performs weighted average in the spatial domain and the pixel-range domain. The method retains important edge texture information when it reduces the perturbations in the image. Then, a three-layer denoising reduction autoencoder is designed, and a new optimization algorithm is proposed to minimize the distance between the input and output. Finally, experiments show that the method proposed has a better defense effect than the existing defense methods. When facing the projected gradient descent-based object detection bounding box disappearance adversarial attack, our defense method can improve the detection true-box rate indicator to 83.04% on the visual object classes challenge (VOC) dataset and 72.20% on the common objects in context (COCO) data. The number of bounding boxes correctly detected is 88.09% and 86.09% of the original one on the PASCAL VOC dataset and the Microsoft COCO dataset, respectively.

Exploring human-nature interactions in national parks with social media photographs and computer vision.

Understanding the activities and preferences of visitors is crucial for managing protected areas and planning conservation strategies. Conservation culturomics promotes the use of user-generated online content in conservation science. Geotagged social media content is a unique source of in situ information on human presence and activities in nature. Photographs posted on social media platforms are a promising source of information, but analyzing large volumes of photographs manually remains laborious. We examined the application of state-of-the-art computer-vision methods to studying human-nature interactions. We used semantic clustering, scene classification, and object detection to automatically analyze photographs taken in Finnish national parks by domestic and international visitors. Our results showed that human-nature interactions can be extracted from user-generated photographs with computer vision. The different methods complemented each other by revealing broad visual themes related to level of the data set, landscape photogeneity, and human activities. Geotagged photographs revealed distinct regional profiles for national parks (e.g., preferences in landscapes and activities), which are potentially useful in park management. Photographic content differed between domestic and international visitors, which indicates differences in activities and preferences. Information extracted automatically from photographs can help identify preferences among diverse visitor groups, which can be used to create profiles of national parks for conservation marketing and to support conservation strategies that rely on public acceptance. The application of computer-vision methods to automatic content analysis of photographs should be explored further in conservation culturomics, particularly in combination with rich metadata available on social media platforms.

Peri-Implant Bone Loss Measurement Using a Region-Based Convolutional Neural Network on Dental Periapical Radiographs.

Determining the peri-implant marginal bone level on radiographs is challenging because the boundaries of the bones around implants are often unclear or the heights of the buccal and lingual bone levels are different. Therefore, a deep convolutional neural network (CNN) was evaluated for detecting the marginal bone level, top, and apex of implants on dental periapical radiographs. An automated assistant system was proposed for calculating the bone loss percentage and classifying the bone resorption severity. A modified region-based CNN (R-CNN) was trained using transfer learning based on Microsoft Common Objects in Context dataset. Overall, 708 periapical radiographic images were divided into training (n = 508), validation (n = 100), and test (n = 100) datasets. The training dataset was randomly enriched by data augmentation. For evaluation, average precision, average recall, and mean object keypoint similarity (OKS) were calculated, and the mean OKS values of the model and a dental clinician were compared. Using detected keypoints, radiographic bone loss was measured and classified. No statistically significant difference was found between the modified R-CNN model and dental clinician for detecting landmarks around dental implants. The modified R-CNN model can be utilized to measure the radiographic peri-implant bone loss ratio to assess the severity of peri-implantitis.

A Deep Learning-Based Approach for Real-Time Object Detection and Recognition

Object detection and recognition is an essential task in computer vision with numerous real-world applications such as surveillance, self-driving cars, and robotics. In recent years, deep learning-based approaches have significantly improved the accuracy and speed of object detection and recognition. The You Only Look Once version 3 (YOLOv3) algorithm is a popular deep learning-based approach that can detect and recognize objects in real-time. The Common Objects in Context (COCO) dataset is a large-scale dataset with over 330,000 labeled images and more than 2.5 million object instances, making it a popular choice for object detection and recognition tasks. In this paper, we propose a deep learning-based approach for real-time object detection and recognition using the YOLOv3 architecture and COCO dataset. We evaluate our approach based on several performance metrics, including mean average precision (mAP), frames per second (FPS), total object detection time, object detection accuracy, false positive rate, number of detected objects, and mean intersection over union (mIoU). Our results show that our approach achieves a mean average precision of 0.76 on the COCO dataset and a real-time performance of 40 frames per second on a single GPU. Additionally, our approach achieves an object detection accuracy of 93.5%, a false positive rate of 6.5%, and a mean intersection over union of 0.65. Our proposed approach shows promising results for real-time object detection and recognition and can be applied to various real-world applications.

Field detection of tiny pests from sticky trap images using deep learning in agricultural greenhouse

Agricultural pest catches on sticky traps can be used for the early detection and identification of hotspots, as well as for estimating relative abundances of adult pests, occurring in greenhouses. This study aimed to construct a detection model for whitefly and thrips from sticky trap images acquired in greenhouse conditions. An end-to-end model, based on the Faster regional-convolutional neural network (R-CNN), termed ‘TPest-RCNN’, was developed to improve the tiny pest detection accuracy. This architecture was trained using a transfer learning strategy on the Common Objects in Context dataset before training on the tiny pest training set to create the TPest-RCNN model. The new model achieved mean F1 score and average precision of 0.944 and 0.952, respectively, on a validation set. The TPest-RCNN model outperformed the Faster R-CNN architecture and other approaches using handcrafted features (color, shape and/or texture) in detecting multiple species from yellow sticky trap images. The test results also showed the model was robust to detect tiny pests on images of different pest densities and light reflections. Using a linear regression between the manual counts and an automatic detection results using the proposed method on images of 41 days, the determination coefficients reached 99.6% and 97.4% for whitefly and thrips, respectively. These results demonstrated that the proposed method could facilitate rapid gathering of information pertaining to numbers of the abundance of tiny pests in greenhouse agriculture and provide a technical reference for pest monitoring and population estimation.

Object Detection Based on Center Point Proposals

Anchor-based detectors are widely adopted in object detection. To improve the accuracy of object detection, multiple anchor boxes are intensively placed on the input image, yet most of them are invalid. Although anchor-free methods can reduce the number of useless anchor boxes, the invalid ones still occupy a high proportion. On this basis, this paper proposes an object-detection method based on center point proposals to reduce the number of useless anchor boxes while improving the quality of anchor boxes, balancing the proportion of positive and negative samples. By introducing the differentiation module in the shallow layer, the new method can alleviate the problem of missing detection caused by overlapping of center points. When trained and tested on COCO (Common Objects in Context) dataset, this algorithm records an increase of about 2% in APS (Average Precision of Small Object), reaching 27.8%. The detector designed in this study outperforms most of the state-of-the-art real-time detectors in speed and accuracy trade-off, achieving the AP of 43.2 in 137 ms.