Efficient pedestrian detection from aerial vehicles with object proposals and deep convolutional neural networks

2016 ◽  
Author(s):  
Breton Minnehan ◽  
Andreas Savakis
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Pedestrian Detection ◽  
Deep Convolutional Neural Networks ◽  
Aerial Vehicles ◽  
Object Proposals

scholarly journals Deep Convolutional Neural Networks for pedestrian detection

2016 ◽  
Vol 47 ◽  
pp. 482-489 ◽  
Author(s):  
D. Tomè ◽  
F. Monti ◽  
L. Baroffio ◽  
L. Bondi ◽  
M. Tagliasacchi ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Pedestrian Detection ◽  
Deep Convolutional Neural Networks

scholarly journals Improvement of the model of object recognition in aero photographs using deep convolutional neural networks

2021 ◽  
Vol 5 (2 (113)) ◽  
pp. 6-21
Author(s):  
Vadym Slyusar ◽  
Mykhailo Protsenko ◽  
Anton Chernukha ◽  
Pavlo Kovalov ◽  
Pavlo Borodych ◽  
...  
Keyword(s):  
Neural Networks ◽  
Object Recognition ◽  
Unmanned Aerial Vehicles ◽  
Convolutional Neural Networks ◽  
Aerial Photographs ◽  
Problem Solution ◽  
Deep Convolutional Neural Networks ◽  
Test Set ◽  
Aerial Vehicles ◽  
Proposed Model

Detection and recognition of objects in images is the main problem to be solved by computer vision systems. As part of solving this problem, the model of object recognition in aerial photographs taken from unmanned aerial vehicles has been improved. A study of object recognition in aerial photographs using deep convolutional neural networks has been carried out. Analysis of possible implementations showed that the AlexNet 2012 model (Canada) trained on the ImageNet image set (China) is most suitable for this problem solution. This model was used as a basic one. The object recognition error for this model with the use of the ImageNet test set of images amounted to 15 %. To solve the problem of improving the effectiveness of object recognition in aerial photographs for 10 classes of images, the final fully connected layer was modified by rejection from 1,000 to 10 neurons and additional two-stage training of the resulting model. Additional training was carried out with a set of images prepared from aerial photographs at stage 1 and with a set of VisDrone 2021 (China) images at stage 2. Optimal training parameters were selected: speed (step) (0.0001), number of epochs (100). As a result, a new model under the proposed name of AlexVisDrone was obtained. The effectiveness of the proposed model was checked with a test set of 100 images for each class (the total number of classes was 10). Accuracy and sensitivity were chosen as the main indicators of the model effectiveness. As a result, an increase in recognition accuracy from 7 % (for images from aerial photographs) to 9 % (for the VisDrone 2021 set) was obtained which has indicated that the choice of neural network architecture and training parameters was correct. The use of the proposed model makes it possible to automate the process of object recognition in aerial photographs. In the future, it is advisable to use this model at ground stations of unmanned aerial vehicle complex control when processing aerial photographs taken from unmanned aerial vehicles, in robotic systems, in video surveillance complexes and when designing unmanned vehicle systems

Multispectral pedestrian detection based on deep convolutional neural networks

2018 ◽  
Vol 94 ◽  
pp. 69-77 ◽  
Author(s):  
Ya-Li Hou ◽  
Yaoyao Song ◽  
Xiaoli Hao ◽  
Yan Shen ◽  
Manyi Qian ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Pedestrian Detection ◽  
Deep Convolutional Neural Networks
Sign in / Sign up

Export Citation Format

Share Document