Improvement of the model of object recognition in aero photographs using deep convolutional neural networks
| Autor: | Vadym Slyusar, Mykhailo Protsenko, Anton Chernukha, Pavlo Kovalov, Pavlo Borodych, Serhii Shevchenko, Oleksandr Chernikov, Serhii Vazhynskyi, Oleg Bogatov, Kirill Khrustalev |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer science
Energy Engineering and Power Technology Convolutional neural network object recognition Industrial and Manufacturing Engineering Set (abstract data type) deep convolutional neural network Aerial photography Management of Technology and Innovation unmanned aerial vehicle T1-995 Industry Computer vision Sensitivity (control systems) Electrical and Electronic Engineering Technology (General) business.industry Applied Mathematics Mechanical Engineering Cognitive neuroscience of visual object recognition Process (computing) HD2321-4730.9 aerial photograph Computer Science Applications Control and Systems Engineering Test set Stage (hydrology) Artificial intelligence business |
| Zdroj: | Eastern-European Journal of Enterprise Technologies, Vol 5, Iss 2 (113), Pp 6-21 (2021) |
| ISSN: | 1729-4061 1729-3774 |
| DOI: | 10.15587/1729-4061.2021.243094 |
| Popis: | 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 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|