Weather-adaptive flying target detection and tracking from infrared video sequences

Cho

Lecture Notes in Electrical Engineering

et al. 2015

Abstract. In this paper, we propose a spatial and temporal flying target detection method using different types of sensors. By combining the sensors, we can discover the hit time and location more precisely. We designed ta system composition in consideration of protecting sensor system, and implemented a working prototype. In the experiments, we demonstrate its performance depending on the processing module and the accuracy.

Section: Related Workmentioning

confidence: 99%

Localizing a Flying Object on Target Place Using Heterogeneous Binary Sensors

Cho

Lecture Notes in Electrical Engineering

et al. 2015

“…Extensive research is continuously being conducted, as practical results are still far from being perfect. Works 2,3,8 dealing with flying target detection have provided algorithms for various approaches, including infrared or hyperspectral imagery. In this case we concentrate on traditional electro-optical generic cameras, for multiple reasons: they are cheap, provide passive detection capabilities, and have a high visual information content.…”

Section: Detection Of Aerial Targetsmentioning

confidence: 99%

“…Elsewhere, low flying targets are segmented 3 above the sea-sky line, by first locating the skyline, then using neighborhood averaging and directional Sobel operators to enhance the object boundaries. Weng et al present a flying target detection method 8 based on infrared processing which is robust against weather conditions, but is not able to recognize the flying targets. Other works 12,13 present more recent approaches to target tracking and recognition, based on infrared sensing for detection and adaptive feature selection for recognition.…”

Section: Introductionmentioning

confidence: 99%

Visual real-time detection, recognition and tracking of ground and airborne targets

Kovács

Benedek

2011

SPIE Proceedings

This paper presents methods and algorithms for real-time visual target detection, recognition and tracking, both in the case of ground-based objects (surveyed from a moving airborne imaging sensor) and flying targets (observed from a groundbased or vehicle mounted sensor). The methods are highly parallelized and partially implemented on GPU, with the goal of real-time speeds even in the case of multiple target observations. Real-time applicability is in focus. The methods use single camera observations, providing a passive and expendable alternative for expensive and/or active sensors. Use cases involve perimeter defense and surveillance situations, where passive detection and observation is a priority (e.g. aerial surveillance of a compound, detection of reconnaissance drones, etc.).

Automatic Target Recognition XX; Acquisition, Tracking, Pointing, and Laser Systems Technologies XXIV; And Optical Pattern Reco

“…Ref. 4,7, such tasks and weather-adaptivity is addressed by using infrared images. The drawback of such approaches are that while the object detection task becomes easier, the segmentation and recognition tasks will be very hard, since infrared imagery can not provide shapes that are good enough for shape based recognition.…”

Section: Object Extractionmentioning

confidence: 99%

“…Ref. 7 presents a flying target detection method based on infrared processing which is robust against weather conditions, but is not able to recognize the flying targets. The method(s) we present in this paper produce an integrated, image-based solution for segmentation, tracking, recognition, and unusual behavior alerting of flying objects.…”

Section: Introductionmentioning

confidence: 99%

Shape-and-motion-fused multiple flying target recognition and tracking

Kovács

Utasi

2010

This paper presents an automatic approach for camera/image based detection, recognition and tracking of flying objects (planes, missiles, etc.). The method detects appearing objects, and recognizes re-appearing targets. It uses a feature-based statistical modeling approach (e.g. HMM) for motion-based recognition, and an image feature (e.g. shape) based indexed database of pre-trained object classes, suitable for recognition on known and alerting on unknown objects. The method can be used for detection of flying objects, recognition of the same object category through multiple views/cameras and signal on unusual motions and shape appearances.