This paper explores the enhancement of convolutional imageprocessing on a RISC-v based architecture through the implementation of branch prediction (BP) techniques. Con-volution, a critical operation in image process...
详细信息
ISBN:
(数字)9798350350821
ISBN:
(纸本)9798350350838
This paper explores the enhancement of convolutional imageprocessing on a RISC-v based architecture through the implementation of branch prediction (BP) techniques. Con-volution, a critical operation in imageprocessing, is essential for tasks such as edge detection, blurring, and feature extraction. Efficient execution of convolution operations, particularly in a RISC-v architecture, requires effective BP to minimize delays caused by conditional operations. This study presents the development of a 5-stage pipelined 32-bit RISC-v processor, integrated with a 2-bit saturating counter branch predictor using a Branch History Table (BHT). The efficiency of the RISC-v processor was evaluated by synthesizing and implementing it using Xilinx vivado on the Kintex- 7 KC705 Evaluation Platform and testing with a convolution algorithm written in assembly language. Experimental results demonstrate that optimizing BP significantly improves the execution efficiency of convolution operations, making it a promising approach for advanced imageprocessing applications.
Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradi...
详细信息
ISBN:
(纸本)9781713871088
Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial redundancy in image features and saves a considerable amount of unnecessary computation. However, the theoretical efficiency achieved by previous methods can hardly translate into a realistic speedup, especially on the multi-core processors (e.g. GPUs). The key challenge is that the existing literature has only focused on designing algorithms with minimal computation, ignoring the fact that the practical latency can also be influenced by scheduling strategies and hardware properties. To bridge the gap between theoretical computation and practical efficiency, we propose a latency-aware spatial-wise dynamic network (LASNet), which performs coarse-grained spatially adaptive inference under the guidance of a novel latency prediction model. The latency prediction model can efficiently estimate the inference latency of dynamic networks by simultaneously considering algorithms, scheduling strategies, and hardware properties. We use the latency predictor to guide both the algorithm design and the scheduling optimization on various hardware platforms. Experiments on image classification, object detection and instance segmentation demonstrate that the proposed framework significantly improves the practical inference efficiency of deep networks. For example, the average latency of a ResNet-101 on the imageNet validation set could be reduced by 36% and 46% on a server GPU (Nvidia Tesla-v100) and an edge device (Nvidia Jetson TX2 GPU) respectively without sacrificing the accuracy. Code is available at https://***/LeapLabTHU/LASNet.
The predominant function of most facial analysis systems revolves around facial alignment and eye tracking, crucial for locating key facial landmarks in images or videos. While developers have access to various models...
详细信息
Agriculture sector is an important pillar of the global economy. The cotton crop is considered one of the prominent agricultural resources. It is widely cultivated in India, China, Pakistan, USA, Brazil, and other cou...
详细信息
ISBN:
(纸本)9781665462198
Agriculture sector is an important pillar of the global economy. The cotton crop is considered one of the prominent agricultural resources. It is widely cultivated in India, China, Pakistan, USA, Brazil, and other countries of the world. The worldwide cotton crop production is severely affected by numerous diseases such as cotton leaf curl virus (CLCv/CLCuv), bacterial blight, and ball rot. imageprocessing techniques together with machine learning algorithms are successfully employed in numerous fields and have also used for crop disease detection. In this study, we present a deep learning-based method for classifying diseases of the cotton crop, including bacterial blight and cotton leaf curl virus (CLCv). The dataset of cotton leaves showing disease symptoms is collected from various locations in Sindh, Pakistan. We employ the Inception v4 architecture as a convolutional neural network to identify diseased plant leaves in particular bacterial blight and CLCv. The accuracy of the designed model is 98.26% which shows prominent improvement compared to the existing models and systems.
The accurate and timely diagnosis of intracranial tumors is crucial for effective treatment and management. In recent years, magnetic resonance imaging (MRI) has emerged as a valuable tool for detecting and diagnosing...
详细信息
Computer image simulation is used in the development of optical measurement systems and processingalgorithms. It allows the performance of a system or algorithm to be verified and its measurement uncertainty to be as...
Computer image simulation is used in the development of optical measurement systems and processingalgorithms. It allows the performance of a system or algorithm to be verified and its measurement uncertainty to be assessed. Modern algorithms make it possible to achieve sub-pixel accuracy in digital imageprocessing. An example of such algorithms is the cross-correlation processing in Particle imagevelocimetry. Often, standard graphics engines such as Unity 3D and Unreal Engine are used to simulate the images. The purpose of this work is to evaluate the possibility of using these tools to generate images for further processing by subpixel resolution algorithms. This paper presents the results of a computational experiment to estimate the maximum spatial resolution for simulations in Unity 3D. A qualitative and quantitative analysis of the results confirms the possibility of using the tested graphics engine for the analysis of subpixel resolution algorithms for digital imageprocessing.
para>In response to the problems of low accuracy and complex network structure in existing deep learning based monocular image depth estimation algorithms, an improved U-NET [1] monocular image depth estimation met...
详细信息
image captioning involves generating a natural language description that accurately represents the content and context of an image. To achieve this, image captioning utilises various machine learning techniques and fi...
详细信息
This research paper presents an innovative solution to address the multifaceted challenges encountered by banana farmers in Sri Lanka, encompassing the entire spectrum of banana production from pre-harvest to post-har...
详细信息
This paper presents the random spray retinex (RSR) algorithm, which is an efficient image enhancement technique with the potential to improve image quality. However, the computational complexity of the algorithm, as w...
详细信息
暂无评论