SWIR imaging bears considerable advantages over visible-light (color) and thermal images in certain challenging propagation conditions. Thus, the SWIR imaging channel is frequently used in multi-spectral imaging systems (MSIS) for long-range surveillance in combination with color and thermal imaging to improve the probability of correct operation in various day, night and climate conditions. Integration of deep-learning (DL)-based real-time object detection in MSIS enables an increase in efficient utilization for complex long-range surveillance solutions such as border or critical assets control. Unfortunately, a lack of datasets for DL-based object detection models training for the SWIR channel limits their performance. To overcome this, by using the MSIS setting we propose a new cross-spectral automatic data annotation methodology for SWIR channel training dataset creation, in which the visible-light channel provides a source for detecting object types and bounding boxes which are then transformed to the SWIR channel. A mathematical image transformation that overcomes differences between the SWIR and color channel and their image distortion effects for various magnifications are explained in detail. With the proposed cross-spectral methodology, the goal of the paper is to improve object detection in SWIR images captured in challenging outdoor scenes. Experimental tests for two object types (cars and persons) using a state-of-the-art YOLOX model demonstrate that retraining with the proposed automatic cross-spectrally created SWIR image dataset significantly improves average detection precision. We achieved excellent improvements in detection performance in various variants of the YOLOX model (nano, tiny and x).

The concept of Smart City started its development path around two to three decades ago; it has been mainly influenced and driven by radical changes in technological, social and business environments. Big Data, Internet of Things and Networked Cyber-Physical Systems, together with the concepts of Cloud, Fog and Edge Computing, have tremendous impact on the development of Smart City, reforming its frame and tasks and redefining its requirements and challenges. We consider feasible architectures of the IT infrastructure and signal processing, taking into account aspects of Big Data, followed by summary of benefits and main challenges, like security of infrastructure and private data. As a practical example we present a public safety application of multi-sensor imaging system: a smart device with target detection subsystem based on artificial intelligence used for activation of target tracking. The experiments have been performed in the cities of Abu Dhabi and Belgrade, which have very different environment. The experiments have shown the effects of videostreaming compression on thermal imagers and the importance of distributed processing power that optimizes requirements for amount of transmitted data and delay.

Dynamic range of the scene can be significantly wider than the dynamic range of an image because of limitations of A/D conversion. In such a situation, numerous details of the scene cannot be adequately shown on the image. Standard industrial digital cameras are equipped with an auto-exposure function that automatically sets both the aperture value and cameras exposure time. When measuring a scene with atypical distribution of light and dark elements, the indicated auto-exposure time may not be optimal. The aim of work was to improve, with minimal cost, the performance of standard industrial digital cameras. We propose a low complexity method for creating HDRlike image using three images captured with different exposure times. The proposed method consists of three algorithms: (1) algorithm for estimating whether the autoexposure time is optimal, (2) algorithm which determines exposure times for two additional images (one with shorter and another with longer than auto-exposure time), and (3) algorithm for HDR-like imaging based on fusion of three previously obtained images. Method is implemented on FPGA inserted into standard industrial digital camera. Results show that the proposed approach produces high quality HDR-like scene-mapped 8-bit images with minimal computational cost. All improvements may be noticed through the performance evaluation.

Video stabilization is essential for long-range electro-optical systems, especially in situations when the field of view is narrow, since the system shake may produce highly deteriorating effects. It is important that the stabilization works for different camera types, i.e., different parts of the electromagnetic spectrum independently of the weather conditions and any form of image distortion. In this paper, we propose a method for real-time video stabilization that uses only gyroscope measurements, analyze its performance, and implement and validate it on a real-world professional electro-optical system developed at Vlatacom Institute. Camera movements are modeled with 3D rotations obtained by integration of MEMS gyroscope measurements. The 3D orientation estimation quality depends on the gyroscope characteristics; we provide a detailed discussion on the criteria for gyroscope selection in terms of the sensitivity, measurement noise, and drift stability. Furthermore, we propose a method for improving the unwanted motion estimation quality using interpolation in the quaternion domain. We also propose practical solutions for eliminating disturbances originating from gyro bias instability and noise. In order to evaluate the quality of our solution, we compared the performance of our implementation with two feature-based digital stabilization methods. The general advantage of the proposed methods is its drastically lower computational complexity; hence, it can be implemented for a low price independent of the used electro-optical sensor system.

In this paper we describe practical implementation of FPGA based solution for converting signal from cameras with HD-SDI, analogue and camera link interfaces to common HDMI format. Main challenges like: frame rate equalization, image resolution adaptation and acts in case of camera connection loss are described in details. As a practical example we gave details about system with HD-SDI visible light camera, HD MWIR camera and analogue SWIR camera. In order to achieve target visibility in different day/night and meteorological conditions a multi-sensor imaging system combines signals from visible light camera, short wave infrared (SWIR) camera and medium (MWIR) or long (LWIR) wave infrared camera. Usually cameras originate from different vendor, with different interfaces, resolutions and frame rate. In order to enable further processing like image stabilization, enhancement, target tracking and image fusion, formats from all cameras should be converted to the same format.