Trainable visual navigation systems based on deep learning demonstrate potential for robustness of onboard camera parameters and challenging environment. However, a deep model requires substantial computational resources and large labelled training sets for successful training. Implementation of the autonomous navigation and training-based fast adaptation to the new environment for a compact drone is a complicated task. The article describes an original model and training algorithms adapted to the limited volume of labelled training set and constrained computational resource. This model consists of a convolutional neural network for visual feature extraction, extreme-learning machine for estimating the position displacement and boosted information-extreme classifier for obstacle prediction. To perform unsupervised training of the convolution filters with a growing sparse-coding neural gas algorithm, supervised learning algorithms to construct the decision rules with simulated annealing search algorithm used for finetuning are proposed. The use of complex criterion for parameter optimization of the feature extractor model is considered. The resulting approach performs better trajectory reconstruction than the well-known ORB-SLAM. In particular, for sequence 7 from the KITTI dataset, the translation error is reduced by nearly 65.6% under the frame rate 10 frame per second. Besides, testing on the independent TUM sequence shot outdoors produces a translation error not exceeding 6% and a rotation error not exceeding 3.68 degrees per 100 m. Testing was carried out on the Raspberry Pi 3+ single-board computer.

Запропоновано модель детектора об'єктiв i критерiй ефективностi навчання моделi. Модель мiстить 7 перших модулiв згорткової мережi Squeezenet, два згортковi рiзномасштабнi шари, та iнформацiйно-екстремальний класифiкатор. Як критерiй ефективностi навчання моделi детектора розглядається мультиплiкативна згортка частинних критерiїв, що враховує ефективнiсть виявлення об'єктiв на зображеннi та точнiсть класифiкацiйного аналiзу. При цьому додаткове використання алгоритму ортогонального узгодженого кодування при обчисленнi високорiвневих ознак дозволяє збiльшити точнiсть моделi на 4 %. Розроблено алгоритм навчання детектора об'єктiв за умов малого обсягу розмiчених навчальних зразкiв та обмежених обчислювальних ресурсiв, доступних на борту малогабаритного безпiлотного апарату. Суть алгоритму полягає в адаптацiї верхнiх шарiв моделi до доменної областi використання на основi алгоритмiв зростаючого розрiджено кодуючого нейронного газу та симуляцiї вiдпалу. Навчання верхнiх шарiв без вчителя дозволяє ефективно використати нерозмiченi данi з доменної областi та визначити необхiдну кiлькiсть нейронiв. Показано, що за вiдсутностi тонкої настройки згорткових шарiв забезпечується 69 % виявлених об'єктiв на зображеннях тестової вибiрки Inria Aerial Image. При цьому пiсля тонкої настройки на основi алгоритму симуляцiї вiдпалу забезпечується 95 % виявлених об'єктiв на тестових зображеннях. Показано, що використання попереднього навчання без вчителя дозволяє пiдвищити узагальнюючу здатнiсть вирiшальних правил та прискорити iтерацiйний процес знаходження глобального максимуму при навчаннi з учителем на вибiрцi обмеженого обсягу. При цьому усунення ефекту перенавчання здiйснюється шляхом оптимального вибору значення гiперпараметру, що характеризує ступiнь покриття вхiдних даних нейронами мережi Ключовi слова: зростаючий нейронний газ, детектор об'єктiв, iнформацiйний критерiй, алгоритм симуляцiя вiдпалу

No abstract

No abstract

Context. Lightweight model and effective training algorithm of on-board object detection system for a compact drone are developed. The object of research is the process of small object detection on aerial images under computational resource constraint and uncertainty caused by small amount of labeled training data. The subject of the research are the model and training algorithm for detecting small objects on aerial imagery. Objective. Goal of the research is developing efficient model and training algorithm of object detection system for a compact aerial drone under conditions of restricted computing resources and the limited volume of the labeled training set. Methods. The four-stage training algorithm of the object detector is proposed. At the first stage, selecting the type of deep convolutional neural network and the number of low-level layers that is pre-trained on the ImageNet dataset for reusing takes place. The second stage involves unsupervised training of high-level convolutional sparse coding layers using modification of growing neural gas to automatically determine the required number of neurons and provide optimal distributions of the neurons over the data. Its application makes it possible to utilize the unlabeled training datasets for the adaptation of the high-level feature description to the domain application area. At the third stage, there are reduction of output feture map using principan component analysis and building of decision rules. In this case, output feature map is formed by concatenation of feature maps from different level of deep network using upscaling upper maps to uniform shape for each channel. This approach provides more contextual information for efficient recognition of small objects on aerial images. In order to build classifier of output feature map pixels is proposed to use boosted information-extreme learning. Besides that, the extreme learning machine is used to build of regression model for predict bounding box of detected object. Last stage involves fine-tuning of high-level layers of deep network using simulated annealing metaheuristic algorithm in order to approximating the global optimum of complex criterion of training efficiency of detection model. Results. The results obtained on open datasets testify to the suitability of the model and training algorithm for practical usage. The proposed training algorithm utilize 500 unlabeled and 200 labeled training samples to provide 96% correctly detection of objects on the images of the test dataset. Conclusions. Scientific novelty of the paper is a new model and training algorithm for object detection, which enable to achieve high confidence of recognition of small objects on aerial images under computational resource constraint and limited volume of the labeled training set. Practical significance of the paper results consists in the developed model and training algorithm made it possible to reduce requirements for size of labeled training set and computation resources of on-board detection system of aerial drone in tr...