Vehicle Detection Algorithm of Small Target with Feature Fusion
Journal Title: 河南科技大学学报（自然科学版） - Year 2019, Vol 40, Issue 2
Abstract
In the current target detection based on deep convolution neural network, the high-dimensional features lost small-area feature information and target position information, which led to a low recognition rate for small targets. The detection method based on feature layer fusion was proposed. The high-dimensional feature map and the low-dimensional feature map were transformed into the same size through the image interpolation. Each feature map was effectively fused by setting a network self-learning parameter, so that the feature map finally detection had rich semantic information and as much target feature information as possible.Using the method, a simple convolutional neural network model was built to detect the long-distance vehicles in the road scene. The test on the KITTI dataset shows that the model's recall rates are increased by 5. 9%and 14. 6% respectively compared with the mainstream Faster-RCNN and SSD inspection framework.
Authors and Affiliations
Pengfei LUO, Ming LI
Keywords
Related Articles
- EP ID EP422474
- DOI 10.15926/j.cnki.issn1672-6871.2019.02.008
- Views 125
- Downloads 0
Influence of Initial Water Content on Swelling Characteristics of Bentonite
In order to obtain the influence of initial water content on swelling characteristics of bentonite, the laboratory tests of swelling ratio without pressure, swelling ratio under pressure and swelling force were conducted...
Blowup for Classical Solutions of n-Dimensional Euler Equations with Nonlinear Damping
The blowup of classical solutions for initial value of the isentropic Euler equations with nonlinear damping in n-dimensional space was studied. When the initial condition had compact support,by functional methods,the cl...
Design of High-precision Phase Measuring Instrument Based on All Phase FFT Method
To overcome low precision and complex structure of traditional phase measuring instrument, a highprecision phase measuring instrument based on all phase fast Fourier transform algorithm (FFT) was proposed.The STM32F407VG...
Low Temperature Impact Toughness of Self-shielded Flux Cored Wire for Pipeline Steel
Taking BaF_2-Fe_2O_3-Al-Mg slag system self-shielded flux cored wire as research object,the effects of residual Al,N and O mass fraction on low temperature impact toughness of the deposited metal in welding wire was anal...
Relevant Parameter Optimization of Lensless Ghost Imaging
In order to improve the image quality of the lensless ghost imaging, a lensless ghost imaging experimental system with second order was constructed based on the pseudo-thermal light.The effect of the correlation number,...