scholarly journals The implementation of an object detection algorithm on the FT processor

2018 ◽  
Vol 173 ◽  
pp. 03081
Author(s):  
Bin Li ◽  
Shuming Chen ◽  
Chao Yang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Object Detection ◽  
Real Time ◽  
Detection Algorithm ◽  
Utilization Rate ◽  
Time Requirement ◽  
Processor Performance ◽  
Network Algorithm ◽  
Neural Network Algorithm

With the continuous development of automatic drive and neural networks, it is possible to use neural network algorithm to carry out object detection in unmanned driving. Usually, the computation of neural network algorithm is huge. How to efficiently compute the algorithm and meet the real-time requirement is a challenge. In this paper, a sparse neural network algorithm is proposed, which can improve the utilization rate of processors. The object detection algorithm YOLO is implemented on the processor. Its performance is equivalent to the current best processor performance.

Unmanned aerial vehicle reconnaissance image recognition based on convolutional neural network

2021 ◽  
pp. 1-10
Author(s):  
Lipeng Si ◽  
Baolong Liu ◽  
Yanfang Fu
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Image Recognition ◽  
Error Detection ◽  
Convolution Neural Network ◽  
Data Sets ◽  
Small Target ◽  
Network Algorithm ◽  
Neural Network Algorithm ◽  
Real Time Tracking

The important strategic position of military UAVs and the wide application of civil UAVs in many fields, they all mark the arrival of the era of unmanned aerial vehicles. At present, in the field of image research, recognition and real-time tracking of specific objects in images has been a technology that many scholars continue to study in depth and need to be further tackled. Image recognition and real-time tracking technology has been widely used in UAV aerial photography. Through the analysis of convolution neural network algorithm and the comparison of image recognition technology, the convolution neural network algorithm is improved to improve the image recognition effect. In this paper, a target detection technique based on improved Faster R-CNN is proposed. The algorithm model is implemented and the classification accuracy is improved through Faster R-CNN network optimization. Aiming at the problem of small target error detection and scale difference in aerial data sets, this paper designs the network structure of RPN and the optimization scheme of related algorithms. The structure of Faster R-CNN is adjusted by improving the embedding of CNN and OHEM algorithm, the accuracy of small target and multitarget detection is improved as a whole. The experimental results show that: compared with LENET-5, the recognition accuracy of the proposed algorithm is significantly improved. And with the increase of the number of samples, the accuracy of this algorithm is 98.9%.

Water-Inflow Forecast of Submarine Tunnel Based on BP Neural Networks

2011 ◽  
Vol 90-93 ◽  
pp. 2173-2177
Author(s):  
Chen Cai ◽  
Tao Huang ◽  
Xun Li ◽  
Yun Zhen Li
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Bp Neural Network ◽  
Forecast Model ◽  
Water Inflow ◽  
Water Volume ◽  
Network Algorithm ◽  
Forecast Precision ◽  
Neural Network Algorithm ◽  
Computation Analysis

The submarine tunnel water-inflow question has many kinds of factor synthesis influences, has highly the complexity and the misalignment, This article used the BP neural network algorithm to establish the submarine tunnel welling up water volume forecast model and to carry on the computation analysis, The result indicated that this model restraining performance is good, the forecast precision is high and simple feasible. This method has provided a new mentality for the submarine tunnel welling up water volume's forecast.

scholarly journals Comparative Performance Analysis of Neural Network Real-Time Object Detections in Different Implementations

2020 ◽  
Vol 226 ◽  
pp. 02020
Author(s):  
Alexey V. Stadnik ◽  
Pavel S. Sazhin ◽  
Slavomir Hnatic
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Computer Vision ◽  
Performance Analysis ◽  
Object Detection ◽  
Real Time ◽  
Network Architecture ◽  
Neural Network Architecture ◽  
Comparative Performance

The performance of neural networks is one of the most important topics in the field of computer vision. In this work, we analyze the speed of object detection using the well-known YOLOv3 neural network architecture in different frameworks under different hardware requirements. We obtain results, which allow us to formulate preliminary qualitative conclusions about the feasibility of various hardware scenarios to solve tasks in real-time environments.

Implementation of Mail Classification Using Neural Networks of the Second Type Spline Weight Functions

2014 ◽  
Vol 513-517 ◽  
pp. 687-690 ◽  
Author(s):  
Dai Yuan Zhang ◽  
Lei Yang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Recall Rate ◽  
High Accuracy ◽  
Weight Functions ◽  
Network Algorithm ◽  
Neural Network Algorithm ◽  
Sorting Process ◽  
E Mail

How to effectively filter out spam is a topic worthy of further study for the growing proliferation of spam. The main purpose of this paper is to apply a new neural network algorithm to the classification of spam. In this paper, we introduce a second type of spline weight function neural network algorithm, as well as e-mail feature extraction and vectorization, and then introduced the mail sorting process. Experiments show that it can get a relatively high accuracy and recall rate on the spam classification. Therefore, with this new algorithm, we can achieve better classification results.

scholarly journals Neural Networks for Fingerprint Recognition

1993 ◽  
Vol 5 (3) ◽  
pp. 402-418 ◽  
Author(s):  
Pierre Baldi ◽  
Yves Chauvin
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Data Base ◽  
Error Rate ◽  
Fingerprint Recognition ◽  
Network Algorithm ◽  
The Neural Network ◽  
Neural Network Algorithm

After collecting a data base of fingerprint images, we design a neural network algorithm for fingerprint recognition. When presented with a pair of fingerprint images, the algorithm outputs an estimate of the probability that the two images originate from the same finger. In one experiment, the neural network is trained using a few hundred pairs of images and its performance is subsequently tested using several thousand pairs of images originated from a subset of the database corresponding to 20 individuals. The error rate currently achieved is less than 0.5%. Additional results, extensions, and possible applications are also briefly discussed.

Sign in / Sign up

Export Citation Format

Share Document