This paper presents a deep learning-based system for urban traffic monitoring, focusing on the detection and tracking of motorcycles using embedded hardware, due to the high accident rates of this type of vehicle. Dif...
详细信息
This paper presents a deep learning-based system for urban traffic monitoring, focusing on the detection and tracking of motorcycles using embedded hardware, due to the high accident rates of this type of vehicle. Different convolutional neural network (CNN) models were evaluated, including MobileNet-v1-SSD, YOLOv5, and Faster R-CNN, implemented on an NvIDIA Graphics processing Units (GPUs) board as the Jetson Xavier NX (R). The MobileNet-v1-SSD model stands out for its balance between precision (90 %), recall (66 %), and latency (similar to 10 ms), making it ideal for real-time applications. Additionally, a tracking algorithm based on optical flow using the Lucas-Kanade method was developed, complemented with logic for creating and deleting identities (IDs), enabling object tracking in dynamic scenarios with partial occlusions. The system includes a methodology for calculating key traffic variables such as speed and direction by correlating pixels with real-world distances through camera calibration. This approach demonstrates the feasibility of developing complex image-processingapplications based on resource-constrained platforms by leveraging the features of efficient embedded systems such as General Purpose GPUs.
In the current golden age of multimedia, human visualization is no longer the single main target, with the final consumer often being a machine which performs some processing or computer vision tasks. In both cases, d...
详细信息
In the current golden age of multimedia, human visualization is no longer the single main target, with the final consumer often being a machine which performs some processing or computer vision tasks. In both cases, deep learning plays a fundamental role in extracting features from the multimedia representation data, usually producing a compressed representation referred to as latent representation. The increasing development and adoption of deep learning-based solutions in a wide area of multimedia applications have opened an exciting new vision where a common compressed multimedia representation is used for both man and machine. The main benefits of this vision are two-fold: i) improved performance for the computer vision tasks, since the effects of coding artifacts are mitigated;and ii) reduced computational complexity, since prior decoding is not required. This paper proposes the first taxonomy for designing compressed domain computer vision solutions driven by the architecture and weights compatibility with an available spatio-temporal computer vision processor. The potential of the proposed taxonomy is demonstrated for the specific case of point cloud classification by designing novel compressed domain processors using the JPEG Pleno Point Cloud Coding standard under development and adaptations of the PointGrid classifier. Experimental results show that the designed compressed domain point cloud classification solutions can significantly outperform the spatial-temporal domain classification benchmarks when applied to the decompressed data, containing coding artifacts, and even surpass their performance when applied to the original uncompressed data.
Quantum-dot cellular automata (QCA) are one of the most promising alternatives to traditional vLSI technology despite significant current obstacles. The QCA has the advantages of very low power dissipation, faster swi...
详细信息
Quantum-dot cellular automata (QCA) are one of the most promising alternatives to traditional vLSI technology despite significant current obstacles. The QCA has the advantages of very low power dissipation, faster switching speed, and extremely low circuit area, which can be used in designing nano-scale imageprocessing circuits. Morphological operations and processing of digital imageprocessing is a significant topic for researchers because it is widely used for analyzing, enhancing, and modifying images to extract meaningful information or improve their visual quality. imageprocessing is also used for image retrieval and enhancement, image compression, object recognition, machinevision, and medical applications. QCA technology, as a new and leading technology with great potential, can play a fundamental role in morphological operations, processing digital images, image editing, medical imaging, facial recognition, and autonomous vehicles. In recent years, researchers in this field have presented many circuits, but they have many flaws in terms of speed, accuracy, and area consumption, and the need to create more efficient circuits is felt more than ever. Therefore, in this article, a new design for morphological operations and processing digital images is presented using QCA technology. This paper presents a new efficient QCA-based implementation of imageprocessing based on the direct interactions between the QCA cells. This circuit uses two majority gates of five new inputs to produce the output and produces the desired output. In addition, a comparison and analysis of the area and clocking complexity, design cost, and energy dissipation through simulation using QCADesigner and QCADesigner-E are done. The results show that the presented circuit produces the expected and correct output results in 0.75 clock phases, and the obtained results show the high speed and low consumption space of the presented circuit. In addition, the presented circuit performs better
Since the preceding decade, there has been a great deal of interest in forecasting landslides using remote-sensing images. Early detection of possible landslide zones will help to save lives and money. However, this a...
详细信息
imageprocessing with computer vision, particularly in the realm of projective geometry, offers remarkable potential for various applications. Through the lens of projective geometry, images can be transformed, augmen...
详细信息
This article presents a real-time edge image extraction CMOS image sensor (CIS) with an edge-detection counter for machinevisionapplications. By examining a conventional column-parallel (CP) CIS imaging structure wi...
详细信息
This article presents a real-time edge image extraction CMOS image sensor (CIS) with an edge-detection counter for machinevisionapplications. By examining a conventional column-parallel (CP) CIS imaging structure with a single-slope analog-to-digital convertor (SS ADC), it discovered an additional time slot available to extract information of an additional image during a normal imaging operation of two adjacent columns. While obtaining a normal image in this study, the prototype CIS with the proposed edge-detection counter effectively utilizes the spare time for extracting an additional column edge image without an image signal processor (ISP) and any computational latency. In addition, by applying a proposed variable edge thresholding function, the proposed CIS can adopt an optimum edge threshold value according to its imaging condition, alleviating an inherent limitation of a column edge image. This prototype CIS was fabricated using a 0.18-mu m 1-poly 6-metal (1P6M) CMOS process with an effective pixel resolution of 320 (H) x 320 (v). The prototype consumes 17.72-mW power with a frame rate of 240 frames/s. The prototype CIS demonstrated a figure of merit of 721 pW/frame pixel.
Amber is a system-on-chip (SoC) with a coarse-grained reconfigurable array (CGRA) for acceleration of dense linear algebra applications, such as machine learning (ML), imageprocessing, and computer vision. It is desi...
详细信息
Amber is a system-on-chip (SoC) with a coarse-grained reconfigurable array (CGRA) for acceleration of dense linear algebra applications, such as machine learning (ML), imageprocessing, and computer vision. It is designed using an agile accelerator-compiler codesign flow;the compiler updates automatically with hardware changes, enabling continuous application-level evaluation of the hardware-software system. To increase hardware utilization and minimize reconfigurability overhead, Amber features the following: 1) dynamic partial reconfiguration (DPR) of the CGRA for higher resource utilization by allowing fast switching between applications and partitioning resources between simultaneous applications;2) streaming memory controllers supporting affine access patterns for efficient mapping of dense linear algebra;and 3) low-overhead transcendental and complex arithmetic operations. The physical design of Amber features a unique clock distribution method and timing methodology to efficiently layout its hierarchical and tile-based design. Amber achieves a peak energy efficiency of 538 INT16 GOPS/W and 483 BFloat16 GFLOPS/W. Compared with a CPU, a GPU, and a field-programmable gate array (FPGA), Amber has up to 3902x , 152x, and 107x better energy-delay product (EDP), respectively.
Fatigued drivers often cause traffic accidents. This study introduces a novel method for detecting fatigue that combines machine learning and imageprocessing techniques. We propose a unique approach that utilizes the...
详细信息
Industry 4.0 conceptualizes the automation of processes through the introduction of technologies such as artificial intelligence and advanced robotics, resulting in a significant production improvement. Detecting defe...
详细信息
Industry 4.0 conceptualizes the automation of processes through the introduction of technologies such as artificial intelligence and advanced robotics, resulting in a significant production improvement. Detecting defects in the production process, predicting mechanical malfunctions in the assembly line, and identifying defects of the final product are just a few examples of applications of these technologies. In this context, this work focuses on the detection of ultrasound probes' surface defects, with a focus on Esaote S.p.A.'s production line probes. To date, this control is performed manually and therefore biased by many factors such as surface morphology, color, size of the defect, and by lighting conditions (which can cause reflections preventing detection). To overcome these shortfalls, this work proposes a fully automatic machinevision system for surface acquisition of ultrasound probes coupled with an automated defect detection system that leverage artificial intelligence. The paper addresses two crucial steps: (i) the development of the acquisition system (i.e., selection of the acquisition device, analysis of the illumination system, and design of the camera handling system);(ii) the analysis of neural network models for defect detection and classification by comparing three possible solutions (i.e., MMSD-Net, ResNet, EfficientNet). The results suggest that the developed system has the potential to be used as a defect detection tool in the production line (full image acquisition cycle takes similar to 200 s), with the best detection accuracy obtained with the EfficientNet model being 98.63% and a classification accuracy of 81.90%.
暂无评论