Detection of small moving objects is an important research area with applications including monitoring of flying insects, studying their foraging behavior, using insect pollinators to monitor flowering and pollination of crops, surveillance of honeybee colonies, and tracking movement of honeybees. However, due to the lack of distinctive shape and textural details on small objects, direct application of modern object detection methods based on convolutional neural networks (CNNs) shows considerably lower performance. In this paper we propose a method for the detection of small moving objects in videos recorded using unmanned aerial vehicles equipped with standard video cameras. The main steps of the proposed method are video stabilization, background estimation and subtraction, frame segmentation using a CNN, and thresholding the segmented frame. However, for training a CNN it is required that a large labeled dataset is available. Manual labelling of small moving objects in videos is very difficult and time consuming, and such labeled datasets do not exist at the moment. To circumvent this problem, we propose training a CNN using synthetic videos generated by adding small blob-like objects to video sequences with real-world backgrounds. The experimental results on detection of flying honeybees show that by using a combination of classical computer vision techniques and CNNs, as well as synthetic training sets, the proposed approach overcomes the problems associated with direct application of CNNs to the given problem and achieves an average F1-score of 0.86 in tests on real-world videos.

No abstract

Free-flying honeybees can electrostatically collect particles from air in the flying and foraging areas, which in conjunction with organic-based explosive vapor sensing films, placed at the entrance to the beehive, can be used as a passive explosive sensing mechanism. Moreover, bees can be trained to actively search for a smell of explosive. Using trained honeybees in conjunction with a system for honeybee localization enables generation of a spatial-time honeybee density map, where the most visited places point to suspicious areas. In both methods (passive and active), bees' activity monitoring plays a significant role, providing information about environmental parameters and activities of bees at the entrance and exit of a beehive. In this paper we present the design and realization of an electronic system for bee activity monitoring at the front of a hive while using bees for explosive detection. The system also monitors air temperature and relative humidity. Results obtained to date from activity monitoring are useful in planning testing activities within our active and passive method, as it can determine the optimal period of the day and environmental parameters in which bees are most active.

No abstract

The objective of this paper is to evaluate Bagof-Colors (BoC) descriptor for land use classification. BoC can be used either as a global or local descriptor. In this paper we present and evaluate both approaches. We analyze the influence of different parameters on classification accuracy and introduce a modification of descriptor extraction process, which significantly influences the classification results and performance.