No abstract

No abstract

Connected Component Analysis (CCA) plays an important role in several image analysis and pattern recognition algorithms. Being one of the most time-consuming tasks in such applications, specific hardware accelerator for the CCA are highly desirable. As its main characteristic, the design of such an accelerator must be able to complete a run-time process of the input image frame without suspending the input streaming data-flow, by using a reasonable amount of hardware resources. This paper presents a new approach that allows virtually any feature of interest to be extracted in a single-pass from the input image frames. The proposed method has been validated by a proper system hardware implemented in a complete heterogeneous design, within a Xilinx Zynq-7000 Field Programmable Gate Array (FPGA) System on Chip (SoC) device. For processing 640 × 480 input image resolution, only 760 LUTs and 787 FFs were required. Moreover, a frame-rate of ~325 fps and a throughput of 95.37 Mp/s were achieved. When compared to several recent competitors, the proposed design exhibits the most favorable performance-resources trade-off.

Connected component analysis is one of the most fundamental steps used in several image processing systems. This technique allows for distinguishing and detecting different objects in images by assigning a unique label to all pixels that refer to the same object. Most of the previous published algorithms have been designed for implementation by software. However, due to the large number of memory accesses and compare, lookup, and control operations when executed on a general-purpose processor, they do not satisfy the speed performance required by the next generation high performance computer vision systems. In this paper, we present the design of a new Connected Component Labeling hardware architecture suitable for high performance heterogeneous image processing of embedded designs. When implemented on a Zynq All Programmable-System on Chip (AP-SOC) 7045 chip, the proposed design allows a throughput rate higher of 220 Mpixels/s to be reached using less than 18,000 LUTs and 5000 FFs, dissipating about 620 µJ.

Due to the huge requirements in terms of both computational and memory capabilities, implementing energy-efficient and high-performance Convolutional Neural Networks (CNNs) by exploiting embedded systems still represents a major challenge for hardware designers. This paper presents the complete design of a heterogeneous embedded system realized by using a Field-Programmable Gate Array Systems-on-Chip (SoC) and suitable to accelerate the inference of Convolutional Neural Networks in power-constrained environments, such as those related to IoT applications. The proposed architecture is validated through its exploitation in large-scale CNNs on low-cost devices. The prototype realized on a Zynq XC7Z045 device achieves a power efficiency up to 135 Gops/W. When the VGG-16 model is inferred, a frame rate up to 11.8 fps is reached.

No abstract

No abstract

Connected component labeling is one of the most important processes for image analysis, image understanding, pattern recognition, and computer vision. It performs inherently sequential operations to scan a binary input image and to assign a unique label to all pixels of each object. This paper presents a novel hardware-oriented labeling approach able to process input pixels in parallel, thus speeding up the labeling task with respect to state-of-the-art competitors. For purposes of comparison with existing designs, several hardware implementations are characterized for different image sizes and realization platforms. The obtained results demonstrate that frame rates and resource efficiency significantly higher than existing counterparts are achieved. The proposed hardware architecture is purposely designed to comply with the fourth generation of the advanced extensible interface (AXI4) protocol and to store intermediate and final outputs within an off-chip memory. Therefore, it can be directly integrated as a custom accelerator in virtually any modern heterogeneous embedded system-on-chip (SoC). As an example, when integrated within the Xilinx Zynq-7000 X C7Z020 SoC, the novel design processes more than 1.9 pixels per clock cycle, thus furnishing more than 30 2k × 2k labeled frames per second by using 3688 Look-Up Tables (LUTs), 1415 Flip Flops (FFs), and 10 kb of on-chip memory.