Usage of Saliency Prior Maps for Detection of Salient Object Features

Introduction:Saliency detection is a fundamental task of computer vision. Its ultimate aim is to localize the objects of interest that grab human visual attention with respect to the rest of the image. A great variety of saliency models based on different approaches was developed since 1990s. In recent years, the saliency detection has become one of actively studied topic in the theory of Convolutional Neural Network (CNN). Many original decisions using CNNs were proposed for salient object detection and, even, event detection.Purpose:A detailed survey of saliency detection methods in deep learning era allows to understand the current possibilities of CNN approach for visual analysis conducted by the human eyes’ tracking and digital image processing.Results:A survey reflects the recent advances in saliency detection using CNNs. Different models available in literature, such as static and dynamic 2D CNNs for salient object detection and 3D CNNs for salient event detection are discussed in the chronological order. It is worth noting that automatic salient event detection in durable videos became possible using the recently appeared 3D CNN combining with 2D CNN for salient audio detection. Also in this article, we have presented a short description of public image and video datasets with annotated salient objects or events, as well as the often used metrics for the results’ evaluation.Practical relevance:This survey is considered as a contribution in the study of rapidly developed deep learning methods with respect to the saliency detection in the images and videos.

Download Full-text

Evaluation of the expediency of using thermal i magery data for decryption exogenous processes and vegetation

Geodesy and Cartography ◽

10.22389/0016-7126-2018-933-3-52-62 ◽

2018 ◽

Vol 933 (3) ◽

pp. 52-62

Author(s):

V.S. Tikunov ◽

I.A. Rylskiy ◽

S.B. Lukatzkiy

Keyword(s):

Spatial Data ◽

Laser Scanning ◽

Data Extraction ◽

Spectral Band ◽

Information Provision ◽

Lidar Data ◽

Thermal Imagery ◽

Scanning Lidar ◽

Field Works ◽

Object Features

Innovative methods of aerial surveys changed approaches to information provision of projecting dramatically in last years. Nowadays there are several methods pretending to be the most efficient for collecting geospatial data intended for projecting – airborne laser scanning (LIDAR) data, RGB aerial imagery (forming 3D pointclouds) and orthoimages. Thermal imagery is one of the additional methods that can be used for projecting. LIDAR data is precise, it allows us to measure relief even under the vegetation, or to collect laser re-flections from wires, metal constructions and poles. Precision and completeness of the DEM, produced from LIDAR data, allows to define relief microforms. Airborne imagery (visual spectrum) is very widespread and can be easily depicted. Thermal images are more strange and less widespread, they use different way of image forming, and spectral features of ob-jects can vary in specific ways. Either way, the additional spectral band can be useful for achieving additional spatial data and different object features, it can minimize field works. Here different aspects of thermal imagery are described in comparison with RGB (visual) images, LIDAR data and GIS layers. The attempt to estimate the feasibility of thermal imag-es for new data extraction is made.

Download Full-text