No abstract available.
Proceeding Downloads
Image Data Augmentation Method based on Style Transfer
Because there aren't enough accessible images of military vehicles, overfitting is a common occurrence when using a detection model in the military sector. Besides, low-contrast military vehicles are more difficult to be spotted in the field. Therefore, ...
FPGA hardware implementation of Q-learning algorithm with low resource consumption
Q-learning is a kind of reinforcement learning, having a wide range of applications varying in different fields. However, in some circumstances like robot control which has shorter training time requirement, Q-learning algorithm implemented on GPU or ...
A Machine-Learning Pipeline for Semantic-Aware and Contexts-Rich Video Description Method
Video description (VD) methods use machine learning to automatically generate sentences to describe video contents. Global-description based VD (gVD) methods generates global description to provide the big picture of video scenes but they lack finer ...
Multi-Scale and Kernel-Predicting Convolutional Networks for Monte Carlo Denoising
Monte Carlo rendering has been widely used in many fields, such as movies, which pursue the photorealistic rendering effect. Monte Carlo rendering needs high sampling rates to get an accurate rendering effect, but the calculation cost is expensive. To ...
Single image dehazing algorithm based on generative adversarial network
This paper proposes a kind of generative adversarial network which is used to remove the haze for single image. In this paper, the generator uses U-Net as the backbone, and in order to effectively fuse the feature of different scales between the non-...
Biparted Hyperboloid and Sphere Intersection Algorithm
Abstract. The focus of this paper is about biparted hyperboloid and sphere intersection algorithm. By coordinate transformation, the generalized cylindrical parametric equation of the biparted hyperboloid is first gained. Then a quartic equation with ...
Optimal sensor deployment in complex 3D terrain surface
Three-dimensional (3D) optimal sensor deployment is to plan the least sensors to cover the surface of the 3D terrain under the condition of reaching a certain coverage rate. Since the existing methods do not consider the terrain obscured effect, a 3D ...
Weakly Supervised Road Garbage Quantification System Based on WCCA
Mechanized road sweeping vehicles are an indispensable part of urban infrastructure. However, while improving work efficiency, the high energy consumption and noise pollution of their high-power dust collectors have become new problems that need to be ...
Online detection of character and 3D surface defect in steel rail production
The surface quality of steel rail is connected to the safety and service life of high-speed rail transportation, and its rail waist character is essential for logistical monitoring and quality traceability. At the moment, it is difficult to use the same ...
The Object Detection of Underwater Garbage with an Improved YOLOv5 Algorithm
Litter deposition in aquatic environments has devastating effects on marine ecological environment and poses a threat to a sustainable economy. Autonomous Underwater Vehicles (AUV) could solve the issue nicely by detecting and clearing litter. A good ...
A Hybrid Model for Evaluation of D&A System
Considering that talent, technology and process are three important components of a port company. To measure and optimise these three main impacts, we process this data using a system called Data and Analysis (D & A).
Our D & A system consists of three ...
The Research and Implementation of Clothing Style Transfer Algorithm Based on CycleGAN
The rapid development of artificial intelligence has brought about changes in many industries, and the application of deep learning technology in apparel design has become a current research hotspot. Since human subjective consciousness plays a dominant ...
A Credit Scoring Ensemble Framework using Adaboost and Multi-layer Ensemble Classification
The accuracy of classification plays a crucial role in the financial industry, and an increase of 1% in the accuracy of credit scoring in credit customer selection, risk measurement, etc. would significantly reduce the losses of financial institutions. ...
An LSTM-based Method for Recognition and Prediction of Aircraft Formation
Aircraft formation recognition and prediction are of great significance in modern air combat. Aiming at the problems of many manual interventions and complex implementation through traditional aircraft formation recognition methods, an intelligent ...
A Regional Logistics Demand Forecasting Method using KPCA-GA-ELM
Logistics demand forecasting works as a basis for well operated city governance especially for e-commerce industry. Yet, how to accurately predict the local logistics demand remains further improvement. To deal with it, this paper proposed an KPCA-GA-...
Air Target Route Rule Mining Based on Clustering
The air target activity is frequent, how to better study and judge the target is an important problem facing at present. The route rule of target is an important feature of judge and recognition. In order to improve the intelligence degree of air target ...
Animaton: Scriptable Finite Automaton for Animation Design in Unity3D Game Engine
In this paper, we propose a novel technical approach for animation design in the Unity3D game engine using the scriptable finite automaton called Animaton that specifies the transitions between positions, rotations, and animation clips for each ...