In recent decades, power generation from Pvsystems has become increasingly popular. However, several environmental variables, such as dust deposition on Pv panels, have significantly reduced Pv energy production. Sev...
详细信息
In present day, many object detection algorithms are available. These computer vision-based object detection algorithms help to detect, locate and trace an object from an image or a video. It requires high speed and a...
详细信息
ISBN:
(数字)9789819713233
ISBN:
(纸本)9789819713226;9789819713233
In present day, many object detection algorithms are available. These computer vision-based object detection algorithms help to detect, locate and trace an object from an image or a video. It requires high speed and accuracy along with efficiency when it is concerned with real-time systems. In machine learning and computer vision, object detection is considered to be an essential research area, also widely implemented in various sectors such as robotic navigation and intelligent video. The traditional approach to object identification consists of the steps as partitioning, clustering, feature extraction and classification. The solution is dependent of manual annotation, which leads to increase in the cost of the algorithm. Due to the diversity of objects, multiple models are needed for feature detection. As a result, classical object detection algorithms have poor generalizability, low detection accuracy, slow operating rate and low robustness. Object detection strategies are widly categorized as one-step and two-step object detection strategies. We are presenting a comparative analysis on object detection algorithms from two categories, i.e. single shot feed forward object detection algorithms and region proposal-based object detection algorithms. Under single shot feed forward, YOLOv7 is being is used along with pretrained weights trained on MS-COCO dataset from scratch. On the contrary, Mask R-CNN is being used to compare with, with its pretrained weights. This study presents a comparative analysis of YOLOv7 and Mask R-CNN in the context of accuracy, memory footprint and processing speed by retraining the models on the dataset of images and videos obtained through real-time systems in constrained.
Approximate computing is an evolving paradigm that aims to improve the power, speed, and area in neural network applications that can tolerate errors up to a specific limit. This letter proposes a new multiplier archi...
详细信息
Approximate computing is an evolving paradigm that aims to improve the power, speed, and area in neural network applications that can tolerate errors up to a specific limit. This letter proposes a new multiplier architecture based on the algorithm that adapts the approximate compressor from the existing and proposed compressors' set to reduce error in the respective partial product columns. Further, the error due to the approximation in the proposed multiplier is corrected using a simple error-correcting module. Results prove that the power and power-delay product (PDP) of an 8-bit multiplier is improved by up to 39.9% and 43.6% compared with the exact multiplier and 27.5% and 23.9% compared to similar previous designs. The proposed multiplier is validated using imageprocessing and neural network applications to prove its efficacy.
image Captioning (ICs) seamlessly combines the realms of Computer vision (Cv) and Natural Language processing (NLP) task involved in producing textual sentences that summarise the image content in a way which is under...
详细信息
With the help of linked device monitoring networks and imageprocessingalgorithms, sensors have lately advanced to a whole new level. Man-animal conflicts, a major issue in the agricultural and forest zones, put huma...
详细信息
The improvement of underwater imaging has advanced significantly due to its contribution to marine engineering and underwater exploration. This fact has been reflected in recent years with the proposal of numerous alg...
详细信息
The improvement of underwater imaging has advanced significantly due to its contribution to marine engineering and underwater exploration. This fact has been reflected in recent years with the proposal of numerous algorithms that improve the quality of underwater images. A benchmarking of three algorithms based on the Retinex models implemented on five high-performance embedded systems is presented herein. These algorithms are the Single Scale Retinex Model (SSR), Multi-Scale Retinex Model (MSR), and the Multi-Scale Retinex Model with Color Restoration (MSRCR). These algorithms perform the histogram equalization to distribute pixels, reduce the predominant color, perform color and contrast correction, and achieve an automatic white balance to improve illumination. This paper employs five edge devices such as Beagle Board, Odroid-XU4, Raspberry Pi 4, Jetson Nano, and Jetson TX2 to enhance underwater images and benchmark their performance. Four quality metrics without a reference image such as UIQM, UCIQUE, BRISQUE and Entropy are used to evaluate the quality of the enhanced underwater images. The MSRCR algorithm achieves the best quality results when it is implemented on Jetson TX2 embedded system. It has a difference of 0.46 s in the processing time of 147 x 196 pixels images concerning a high-performance personal computer (PC). Implementing these algorithms on embedded systems offers an excellent cost-benefit ratio versus a traditional PC, considering image quality metrics, precision, accuracy, energy consumption, price, lightweight, size, portability, and reliability. These findings hold great promise for unmanned and self-propelled underwater vehicles with artificial vision for exploration. (C) 2022 Elsevier B.v. All rights reserved.
Automatic optical recognition of documents is a traditional function of modern document processingsystems. In this context, recognition represents a complex process which includes imageprocessing, segmentation, clas...
详细信息
Automatic optical recognition of documents is a traditional function of modern document processingsystems. In this context, recognition represents a complex process which includes imageprocessing, segmentation, classification, and linguistic analysis. Although the idea of using mobile devices for recognition of paper documents is not new, direct usage of existing software solutions for scanned images recognition yields low recognition precision on images obtained using a mobile device. This is due, first of all, to perspective distortions and lower effective resolution in the latter case. In this paper, we present an original approach and a set of algorithms for recognition of video frame sequence containing a document image, which is suitable for mobile implementation. It is based on a coarse-to-fine methodology, where template matching and fields localization are performed on the image with lowered resolution, followed by lazy processing of parts of the images only corresponding to the fields which are not recognized yet. video stream is utilized as a source of noise reduction both in coordinates of the fields and optical character recognition classifiers outputs. The algorithm based on the proposed approach is suitable for running on the device itself and can operate even when none of the video frames contain a document image of sufficient quality by themselves.
The technology and decomposition algorithm for accelerating the processing of geoinformation data based on the distribution of samples of dynamic and quasi-static data using the analysis of eigenvalues of matrices obt...
详细信息
The technology and decomposition algorithm for accelerating the processing of geoinformation data based on the distribution of samples of dynamic and quasi-static data using the analysis of eigenvalues of matrices obtained by means of iterative calculation according to the Khilenko's method are proposed. The algorithm is aimed at processing large geoinformation data arrays. Comparative results of model calculations using known computation methods are given.
Alzheimer's disease (AD) is a neurodegenerative condition that deteriorates brain cells and impairs a patient's memory. It is progressive and incurable. Early identification can shield the patient from more br...
详细信息
ISBN:
(纸本)9798350391558;9798350379990
Alzheimer's disease (AD) is a neurodegenerative condition that deteriorates brain cells and impairs a patient's memory. It is progressive and incurable. Early identification can shield the patient from more brain cell damage and, as a result, help them avoid irreversible memory loss. The scientific community has employed a number of deep learning algorithms to automatically identify Alzheimer's patients. These comprise binary classification of patient scans into stages of AD as well as moderate cognitive impairment (MCI). Limited research has been done on the multiclass classification of Alzheimer's disease (AD) up to six distinct stages. This research proposes novel technique in Alzheimer disease detection with severity level analysis utilizing deep learning (DL) model. Input is collected as MRI brain images and processed for noise removal and smoothening. Then processed image classification and disease stage is detected using pre-trained multi-layer convolutional residual transfer Random Forest with Inceptionv3 model. Experimental analysis is carried out in terms of training accuracy, mean average mean average precision, sensitivity, AUC for various MRI brain image dataset. Training accuracy attained by proposed technique is 96%, mean average precision of 93%, sensitivity of 95%, AUC of 90%.
A large number of computer vision algorithms in their work use information about geometric parameters of objects in images. For such algorithms, an important element of their performance and efficiency is the calibrat...
详细信息
暂无评论