A Review: Object Detection Models

Kısırlık son 50 yılda dünya çapında önemli bir sağlık problemi haline gelmiştir. Dünyanın farklı bölgelerine göre oranı değişen bu problem ortalama olarak dünyadaki her on çiften birini etkilemektedir. Erkek kaynaklı kısırlık teşhisi, sperm kalitesi değerlendirilerek yapılır. Sperm kalitesi araştırılırken sperm sayısı, hareketi ve morfolojik yapısı değerlendirilir. Sperm hareketi ve sayımının analizi öncesinde sperm tespiti önemli bir adımdır. Bu çalışmada, oluşturulan özgün yeni semen video veri kümesi üzerinde Faster R-CNN ve YOLOv3 derin öğrenme yöntemleri kullanılarak otonom sperm tespiti gerçekleştirilmiştir. Çalışma kapsamında oluşturulan bu özgün veri kümesi, mikroskop altında semen örneklerinin cep telefonu yardımı ile elde edilen 10 hastaya ait semen videolarını ve içeriğindeki nesnelerin sperm ve sperm olmayan şeklindeki etiket bilgisini içermektedir. Analiz için hazırlanmış etiketli videolar hasta odaklı ve hasta bağımsız olmak üzere iki senaryo ile değerlendirilmiştir. İlk senaryomuzda etiketli sekiz video birleştirilerek Faster R-CNN ve YOLOv3 modelleri 3 farklı oranda oluşturulmuş veriler ile eğitilmiş ve test edilmiştir. İkinci senaryoda ise eğitilmiş her bir modelimiz daha önce eğitime hiç katılmamış iki video ile test edilmiştir. İkinci senaryomuzda, eğitimine hiç katılmamış videolar kullanılarak algılama performansları değerlendirilmiştir. Yapılan çalışmada YOLOv3 modeli ile bireysel videolarda %96, ortalama da ise %84,5 gibi mAP sperm tespit sonuçları elde edilmiştir. Sonuçlar nesne tespitinin doğruluğu ve eğitim süreleri gibi iki önemli kriter ile karşılaştırıldığında YOLOv3 yöntemi Faster R-CNN yönteminden daha başarılı olduğu gözlemlenmiştir.

Object detection typically assumes that training and test data are drawn from an identical distribution, which, however, does not always hold in practice. Such a distribution mismatch will lead to a significant performance drop. In this work, we aim to improve the cross-domain robustness of object detection. We tackle the domain shift on two levels: (1) the image-level shift, such as image style, illumination, etc., and (2) the instance-level shift, such as object appearance, size, etc. We build our approach based on the recent state-of-the-art Faster R-CNN model, and design two domain adaptation components, on image level and instance level, to reduce the domain discrepancy. The two domain adaptation components are based on <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">H</i> -divergence theory, and are implemented by learning a domain classifier in adversarial training manner. The domain classifiers on different levels are further reinforced with a consistency regularization to learn a domain-invariant region proposal network (RPN) in the Faster R-CNN model. We evaluate our newly proposed approach using multiple datasets including Cityscapes, KITTI, SIM10K, etc. The results demonstrate the effectiveness of our proposed approach for robust object detection in various domain shift scenarios.

In this article, Faster R-CNN object detection algorithm is used for automatic weapon detection in X-Ray bag images obtained from security points. In the proposed method, Faster R-CNN model was fed by creating 2 different 3 band images. In the first one, the 3 bands of the image are equalized to the high energy values obtained from the X-Ray device. In the other one, 1st band is equalized to high values, 2nd band is equalized to low values and the 3rd band is equalized to the difference between high energy and low energy values. Performance values of the two different image generation techniques that fed the deep learning model were compared. In the study, X-Ray dataset provided by HTR Company was used. When the results are evaluated, it is seen that Faster R-CNN method can be used in weapon detection with very high performance as a deep learning model and the method of creating images that feed the model has an effect on object detection performance.

Indian traffic sign detection and recognition using deep learning

Over the past few years, deep learning has played a tremendous role in real time object detection, recognition and classification. Today, algorithms use deep learning not only for simple object detection but have also paved way for vehicle detection that is complex situation such as Indian roads. Different deep learning models can learn features of varied complexity and perform according to surrounding environment in which they are deployed. In this paper a comparison of six models is performed for detection of vehicles on roads that are unstructured or unconstrained. Till date, deep learning algorithms are being used for vehicle (car, bus, truck, motorcycle etc.) detection. A dataset based on Indian road scenario has been used for training on models: faster RCNN and Single Shot Detector (SSD) combined with convolution classifiers mobilenet, resnet and inceptionnet. The six models are compared by evaluating mean average precision (mAP) and classification time complexity for IDD dataset. The observations suggested faster RCNN Resnet50 resolves the trade-off of time and accuracy. Whereas SSD mobilenet V1 takes 31.89% less time than faster RCNN resnet101. On the flipped side, faster RCNN resnet101is 34.38% more accurate than SSD mobilenet v1.

Detection of metastasis of mediastinal lymph nodes in lung cancer patients with an artificial intelligence model.

In computer vision, significant advances have been made in recent years on object recognition and detection with the rapid development of deep learning, especially deep convolutional neural networks (CNN). The majority of deep learning methods for object detection have been developed for large objects and their performances on small-object detection are not very good. This paper contributes to research in low-resolution small-object detection by evaluating the performances of leading deep learning methods for object detection using a common dataset, which is a new dataset for bird detection, called Little Birds in Aerial Imagery (LBAI), created from real-life aerial imagery data. LBAI contains birds with sizes ranging from 10px to 40px. In our experiments, some of the best deep learning architectures were implemented and applied to LBAI, which include object detection techniques such as YOLOv2, SSH, and Tiny Face, in addition to small instance segmentation techniques including U-Net and Mask R-CNN. Among the object detection methods, experimental results demonstrated that SSH performed the best for easy cases, whereas Tiny Face performed the best for hard cases, i.e. where a cluttered background makes detecting birds difficult. Among small instance segmentation methods, experimental results revealed U-Net achieved slightly better performance than Mask R-CNN.

Basic tasks in computer vision, object detection and localization have many applications in autonomous driving, robotics, surveillance, and healthcare [1]. Deep learning has enabled previously unheard-of levels of accuracy and robustness in object detection and localization tasks, revolutionizing the area in recent years. This paper provides a thorough overview of the most recent developments and approaches in the application of deep learning algorithms for localization and object detection. First, we go over the basic ideas behind object identification and localization, emphasizing the difficulties caused by different item sizes, occlusions, and cluttered backgrounds. We then explore the nuances of deep learning architectures designed specifically for these kinds of tasks: anchor-free approaches like Center Net, single-shot detectors like YOLO, and region-based detectors like Faster R-CNN. We investigate feature extraction networks, object detecting heads, and training procedures for best performance as we investigate the underlying mechanics of these architectures. We also go over important assessment measures and datasets that are necessary for benchmarking and training object detection algorithms. We stress the significance of using strong evaluation techniques to guarantee the dependability and capacity for generalization of the suggested algorithms. Apart from technical concerns, we investigate practical uses cases where object detection and localization are essential, like autonomous vehicle pedestrian identification, surveillance system object tracking, and medical imaging anomaly detection. Lastly, we examine new developments and directions for the discipline, such as integrating multimodal data, handling domain shifts, and improving object detection algorithms' interpretability and fairness. Our goal is to stimulate further developments in computer vision systems by offering scholars, professionals, and hobbyists insightful knowledge about the problems and cutting-edge methods of object recognition and localization through this thorough review. The content of the paper is succinctly summarized in this abstract, which also highlights the significance of deep learning, object detection and localization, important methodology, datasets, applications, and future developments in the field.

In recent years, a lot of research has been conducted in the field of object detection for aerial image, and many effective methods have emerged. This paper enhances the existing Faster RCNN model to achieve better detection accuracy. We improve the feature extraction of Faster RCNN model using multi-scale feature fusion. Compared with the traditional Faster RCNN model, the accuracy on mAP is improved by 1.06% by applying the proposed method. The visual effects and numerical results of object detection verify the improvement of the proposed method.

Autonomous vehicles (AV s) are the future of trans-portation and are likely to bring countless benefits compared to human-operated driving. However, there are still a lot of advances to be made before these vehicles can be considered completely safe and before they can reach full autonomy. Perceiving the environment with the utmost accuracy and speed is crucial for autonomous vehicles. Hence, making this process more efficient and streamlined is of paramount importance. In order to perceive the environment, AV s need to classify and localize the different objects in the surrounding. For this research, we deal with the detection of occluded objects to help enhance the perception of AV s. We introduce a new dataset containing occluded instances of road scenes from the perspective of Bangladesh. We utilized transfer learning to train the YOLOv5, YOLOX, and Faster R-CNN models, using their respective pre-trained weights on the COCO dataset. We then evaluate and compare the performance of the three object detection algorithms on our dataset. YOLOv5, YOLOX, and Faster R-CNN achieved mean Average Precision (mAP) at 0.5 of 0.777, 0.849, and 0.688, and mAP at 0.5:0.95 of 0.546, 0.634, and 0.422, respectively, in our test set. Therefore, we find YOLOX to be the best performing model on our dataset, and its high mAP scores demonstrate the effectiveness of the model as well as the dataset.

Deep learning-based object detection in low-altitude UAV datasets: A survey

The object detection approaches in conjunction with Fast/Faster R-CNN and YOLO have shown the benchmarking performance on several occasions. Inspired by the Refine Net, we propose a new model called Faster+ R-CNN based on Faster R-CNN, which is mainly based on iterative refinement on the proposed regions. The Faster+ R-CNN model can iteratively refine the region proposal based on previous output. We trained and tested our new model on PASCAL VOC 2007 dataset, and experiments showed that our method can iteratively improve the mean average precision (mAP) from 0.6702 to 0.6764 in object detecting task. We also demonstrate the facial detection results using the Faster+ R-CNN on the widely used Face Detection Dataset and Benchmark (FDDB) benchmark. By training the Faster+ R-CNN model on the large scale WIDER face dataset, we report the improved results on two widely used face detection benchmarks including FDDB.

WITHDRAWN: MRI based detection and classification of brain tumor using enhanced faster R-CNN and Alex Net model

In this paper, we will study the basic flow and the principle of state-of-the-art object detection technique (i.e. Faster R-CNN) and improve it further with the inclusion of two strategies into it. Firstly, we propose a multi-layer features merging strategy by using a concatenation layer. Secondly, we introduce a contextual learning scheme for Faster R-CNN. Previously, Faster R-CNN just uses regional features. Contextual features are added with the regional features for the classification and detection task. Our improvement on Faster R-CNN shows promising results. We call our improved Faster R-CNN network as ID-CNN (Intelligent Detection Using Convolutional Neural Network) as its detection accuracy is better. Therefore, we call it as an intelligent detector. We use a deep VGG-16 model as our base model, as Faster R-CNN did. We evaluated our ID-CNN on Pascal VOC public datasets. Experimental results show that ID-CNN can effectively improve the object detection average precision to some extent. On VOC 2007 and 2012, we achieved a mean average precision (mAP) of 74.7% and 71.9%, respectively. ID-CNN is also end-to-end trainable with the same alternating fine-tuning optimization scheme of Faster R-CNN. Finally, we compared ID-CNN with Faster R-CNN on ImageNet object detection dataset and we achieved mAP of 48.1% compared with 46.2% for Faster R-CNN.

Unmanned Aerial Vehicles (UAVs) have gained significant traction for real-time surveillance applications such as object tracking and search-and-rescue missions. A key enabler of these capabilities is the integration of a real-time, highly accurate object detection system. While available two-stage detectors like R-CNN, Fast R-CNN, Faster R-CNN, and Mask R-CNN achieve high detection accuracy and precise localization by dividing the image into regions and classifying each region, they are often slow, complex, and resource-intensive, making them unsuitable for real-time applications. To address this limitation, this research utilizes a Darknet-based YOLOv3 (You Only Look Once, Version 3), a state-of-the-art algorithm for real-time object detection in videos, live feeds, and images. Leveraging a deep Convolutional Neural Network (CNN), YOLOv3 efficiently learns features and predicts object locations and class probabilities in a single pass, ensuring high-speed and reliable detection. A real-time aerial surveillance system for quadcopter application using machine vision is proposed. The training dataset, obtained from the internet and self-taken images from a camera, was manually annotated into three critical categories: suspect, bandit, and weapon. The dataset was subsequently divided into training and testing subsets. Experimental results demonstrate that the proposed system achieves outstanding detection accuracy, with an overall mean average precision (mAP@0.5) of 93.82%, precision of 94%, and recall of 83%. Compared to a ResNet-50-based Faster R-CNN model, the YOLOv3-based approach outperformed, achieving success rates of 0.81 for the Bandit class and 1.00 for both Suspect and Weapon classes. This research improves drone-based AI for real-time object detection in security systems, enhancing efficiency and adaptability. It also creates specialized datasets, including a tailored bandit dataset, to support future UAV security research.