- Browse by Subject
Browsing by Subject "object detection"
Now showing 1 - 7 of 7
Results Per Page
Sort Options
Item CoupleNet: Coupling Global Structure with Local Parts for Object Detection(IEEE, 2017-10) Zhu, Yousong; Zhao, Chaoyang; Wang, Jinqiao; Zhao, Xu; Wu, Yi; Lu, Hanqing; Medicine, School of MedicineThe region-based Convolutional Neural Network (CNN) detectors such as Faster R-CNN or R-FCN have already shown promising results for object detection by combining the region proposal subnetwork and the classification subnetwork together. Although R-FCN has achieved higher detection speed while keeping the detection performance, the global structure information is ignored by the position-sensitive score maps. To fully explore the local and global properties, in this paper, we propose a novel fully convolutional network, named as CoupleNet, to couple the global structure with local parts for object detection. Specifically, the object proposals obtained by the Region Proposal Network (RPN) are fed into the the coupling module which consists of two branches. One branch adopts the position-sensitive RoI (PSRoI) pooling to capture the local part information of the object, while the other employs the RoI pooling to encode the global and context information. Next, we design different coupling strategies and normalization ways to make full use of the complementary advantages between the global and local branches. Extensive experiments demonstrate the effectiveness of our approach. We achieve state-of-the-art results on all three challenging datasets, i.e. a mAP of 82.7% on VOC07, 80.4% on VOC12, and 34.4% on COCO. Codes will be made publicly available1.Item Human Iris Image Analysis for the Classification of Fuchs’ Crypts and Peripupillary Rings(Springer, 2022-09-01) Wang, Hao; Fang, Shiaofen; Wilke, Frankie; Larsson, Mats; Walsh, Susan; Computer and Information Science, School of ScienceThe human iris is one of the most important identifiable features that contain many complex patterns. In this work, we attempted to automatically classify irises with machine learning models based on several different iris patterns in order to assist genetic research related to pigmentation and structural tissue differences within the human iris. Specifically, two main iris patterns that are commonly observed in the general population were analyzed: the Fuchs’ crypts and the peripupillary pigmented ring. A two-stage machine learning model was proposed to classify the iris crypt frequency, in which a Mask R-CNN model was first built to identify the number of crypts of each size level in the iris, followed by a SVM model to determine the final category. Another KNN model, which used the area-refined histogram features, was applied to classify the iris based on the peripupillary pigmented ring. The labels used in the images were generated independently by two trained expert raters. The performance of these models was evaluated on a test set with overall accuracies of the models estimated at 80.0% and 86.6% for crypts and pigmented ring, respectively. These optimized objective models were therefore concordant with the inter-rater reliability scores produced by expert human raters.Item NextDet: Efficient Sparse-to-Dense Object Detection with Attentive Feature Aggregation(MDPI, 2022-11-28) Kalgaonkar, Priyank; El-Sharkawy, Mohamed; Electrical and Computer Engineering, School of Engineering and TechnologyObject detection is a computer vision task of detecting instances of objects of a certain class, identifying types of objects, determining its location, and accurately labelling them in an input image or a video. The scope of the work presented within this paper proposes a modern object detection network called NextDet to efficiently detect objects of multiple classes which utilizes CondenseNeXt, an award-winning lightweight image classification convolutional neural network algorithm with reduced number of FLOPs and parameters as the backbone, to efficiently extract and aggregate image features at different granularities in addition to other novel and modified strategies such as attentive feature aggregation in the head, to perform object detection and draw bounding boxes around the detected objects. Extensive experiments and ablation tests, as outlined in this paper, are performed on Argoverse-HD and COCO datasets, which provide numerous temporarily sparse to dense annotated images, demonstrate that the proposed object detection algorithm with CondenseNeXt as the backbone result in an increase in mean Average Precision (mAP) performance and interpretability on Argoverse-HD’s monocular ego-vehicle camera captured scenarios by up to 17.39% as well as COCO’s large set of images of everyday scenes of real-world common objects by up to 14.62%.Item A novel quality assessment for visual secret sharing schemes(Springer, 2017-12) Jiang, Feng; King, Brian; Department of Engineering Technology, School of Engineering and TechnologyTo evaluate the visual quality in visual secret sharing schemes, most of the existing metrics fail to generate fair and uniform quality scores for tested reconstructed images. We propose a new approach to measure the visual quality of the reconstructed image for visual secret sharing schemes. We developed an object detection method in the context of secret sharing, detecting outstanding local features and global object contour. The quality metric is constructed based on the object detection-weight map. The effectiveness of the proposed quality metric is demonstrated by a series of experiments. The experimental results show that our quality metric based on secret object detection outperforms existing metrics. Furthermore, it is straightforward to implement and can be applied to various applications such as performing the security test of the visual secret sharing process.Item Object Detection from a Vehicle Using Deep Learning Network and Future Integration with Multi-Sensor Fusion Algorithm(SAE, 2017-03) Dheekonda, Raja Sekhar Rao; Panda, Sampad K.; Khan, Nazmuzzaman; Al-Hasan, Mohammad; Anwar, Sohel; Mechanical Engineering, School of Engineering and TechnologyAccuracy in detecting a moving object is critical to autonomous driving or advanced driver assistance systems (ADAS). By including the object classification from multiple sensor detections, the model of the object or environment can be identified more accurately. The critical parameters involved in improving the accuracy are the size and the speed of the moving object. All sensor data are to be used in defining a composite object representation so that it could be used for the class information in the core object’s description. This composite data can then be used by a deep learning network for complete perception fusion in order to solve the detection and tracking of moving objects problem. Camera image data from subsequent frames along the time axis in conjunction with the speed and size of the object will further contribute in developing better recognition algorithms. In this paper, we present preliminary results using only camera images for detecting various objects using deep learning network, as a first step toward multi-sensor fusion algorithm development. The simulation experiments based on camera images show encouraging results where the proposed deep learning network based detection algorithm was able to detect various objects with certain degree of confidence. A laboratory experimental setup is being commissioned where three different types of sensors, a digital camera with 8 megapixel resolution, a LIDAR with 40m range, and ultrasonic distance transducer sensors will be used for multi-sensor fusion to identify the object in real-time.Item Real-Time Embedded Implementation of Improved Object Detector for Resource-Constrained Devices(MDPI, 2022-04-13) Ravi, Niranjan; El-Sharkawy, Mohamed; Electrical and Computer Engineering, School of Engineering and TechnologyArtificial intelligence (A.I.) has revolutionised a wide range of human activities, including the accelerated development of autonomous vehicles. Self-navigating delivery robots are recent trends in A.I. applications such as multitarget object detection, image classification, and segmentation to tackle sociotechnical challenges, including the development of autonomous driving vehicles, surveillance systems, intelligent transportation, and smart traffic monitoring systems. In recent years, object detection and its deployment on embedded edge devices have seen a rise in interest compared to other perception tasks. Embedded edge devices have limited computing power, which impedes the deployment of efficient detection algorithms in resource-constrained environments. To improve on-board computational latency, edge devices often sacrifice performance, creating the need for highly efficient A.I. models. This research examines existing loss metrics and their weaknesses, and proposes an improved loss metric that can address the bounding box regression problem. Enhanced metrics were implemented in an ultraefficient YOLOv5 network and tested on the targeted datasets. The latest version of the PyTorch framework was incorporated in model development. The model was further deployed using the ROS 2 framework running on NVIDIA Jetson Xavier NX, an embedded development platform, to conduct the experiment in real time.Item A Transfer Learning Approach to Object Detection Acceleration for Embedded Applications(2021-08) Vance, Lauren M.; Christopher, Lauren; King, Brian; Rizkalla, MaherDeep learning solutions to computer vision tasks have revolutionized many industries in recent years, but embedded systems have too many restrictions to take advantage of current state-of-the-art configurations. Typical embedded processor hardware configurations must meet very low power and memory constraints to maintain small and lightweight packaging, and the architectures of the current best deep learning models are too computationally-intensive for these hardware configurations. Current research shows that convolutional neural networks (CNNs) can be deployed with a few architectural modifications on Field-Programmable Gate Arrays (FPGAs) resulting in minimal loss of accuracy, similar or decreased processing speeds, and lower power consumption when compared to general-purpose Central Processing Units (CPUs) and Graphics Processing Units (GPUs). This research contributes further to these findings with the FPGA implementation of a YOLOv4 object detection model that was developed with the use of transfer learning. The transfer-learned model uses the weights of a model pre-trained on the MS-COCO dataset as a starting point then fine-tunes only the output layers for detection on more specific objects of five classes. The model architecture was then modified slightly for compatibility with the FPGA hardware using techniques such as weight quantization and replacing unsupported activation layer types. The model was deployed on three different hardware setups (CPU, GPU, FPGA) for inference on a test set of 100 images. It was found that the FPGA was able to achieve real-time inference speeds of 33.77 frames-per-second, a speedup of 7.74 frames-per-second when compared to GPU deployment. The model also consumed 96% less power than a GPU configuration with only approximately 4% average loss in accuracy across all 5 classes. The results are even more striking when compared to CPU deployment, with 131.7-times speedup in inference throughput. CPUs have long since been outperformed by GPUs for deep learning applications but are used in most embedded systems. These results further illustrate the advantages of FPGAs for deep learning inference on embedded systems even when transfer learning is used for an efficient end-to-end deployment process. This work advances current state-of-the-art with the implementation of a YOLOv4 object detection model developed with transfer learning for FPGA deployment.