Improving the effectiveness of training the on-board object detection system for a compact unmanned aerial vehicle
Journal Title: Восточно-Европейский журнал передовых технологий - Year 2018, Vol 4, Issue 9
Abstract
<p class="a"><span lang="EN-US">The model of object detector and the criterion of leaning effectiveness of the model were proposed. The model contains 7 first modules of the convolutional Squeezenet network, two convolutional multiscale layers and the informationextreme classifier. The multiplicative convolution of the particular criteria that takes into account the effectiveness of detection of objects in the image and accuracy of the classification analysis was considered as the criterion of learning effectiveness of the model. In this case, additional use of the orthogonal matching pursuit algorithm in calculating highlevel features makes it possible to increase the accuracy of the model by 4 %. The training algorithm of object detector under conditions of a small size of labeled training datasets and limited computing resources available on board of a compact unmanned aerial vehicle was developed. The essence of the algorithm is to adapt the highlevel layers of the model to the domain application area, based on the algorithms of growing sparse coding neural gas and simulated annealing. Unsupervised learning of highlevel layers makes it possible to use effectively the unlabeled datasets from the domain area and determine the required number of neurons. It is shown that in the absence of fine tuning of convolutional layers, 69 % detection of objects in the images of the test dataset Inria Aerial Image was ensured. In this case, after fine tuning based on the simulated annealing algorithm, 95 % detection of the objects in test images is ensured. </span></p><p class="a"><span lang="EN-US">It was shown that the use of unsupervised pretraining makes it possible to increase the generalizing ability of decision rules and to accelerate the iteration process of finding the global maximum during supervised learning on the dataset of limited size. In this case, the overfitting effect is eliminated by optimal selection of the value of hyperparameter, characterizing the measure of coverage of the input data of by network neurons. </span></p>
Authors and Affiliations
Vyacheslav Moskalenko, Anatoliy Dovbysh, Igor Naumenko, Alyona Moskalenko, Artem Korobov
Keywords
Related Articles
- EP ID EP528108
- DOI 10.15587/1729-4061.2018.139923
- Views 59
- Downloads 0
Exploiting the knowledge engineering paradigms for designing smart learning systems
<p class="a">Knowledge engineering (KE) is a subarea of artificial intelligence (AI). Recently, KE paradigms have become more widespread within the fields of smart education and learning. Developing of Smart learning Sys...
Improvement of a rotor film device for the production of highquality multicomponent natural pastes
<p>We have improved a heat exchange system of the rotor film device by using, as a heater, a flexible film resistive electric heater of the radiation type, which repeats the geometry of a working chamber of the device. I...
Research into the process of loading the surface of a vibrosieve when a loose mixture is fed unevenly
<p>The work examines the influence of uneven feeding of a loose mixture on the process of loading a vibrating sieve. In this work, we established regularities of layer thickness, longitudinal and transverse components of...
Investigation of cogging forces using reluctance circuits equivalent approximation in a ladder secondary singlesided linear induction motor
Linear induction motors have recently played an important role in positioning linear motion. However, they suffer a low level of precision for very low speed application. For improving the precision of LIM, especially in...
Application of information technologies for the optimization of itinerary when delivering cargo by automobile transport
<p>We have proven the applicability of modern tools of information technologies to solve a traveling salesman problem using a combinatorial method and a transport problem, which is stated in the form of a road transport...