Fusion of thermal and visible images for day/night moving objects detection

Mouats, Tarek; Aouf, Nabil

doi:10.1109/sspd.2014.6943324

Cited by 10 publications

(8 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…18 The method involved is background subtraction (BS) and combining of thermal and visible images by Gaussian mixture models (GMM). 19 Dynamic adaption of combination method is found as it works simultaneously in day/night and similarly will do the required changes. 19 There are 3 fusion methods.…”

Section: Teju and Bhavanamentioning

confidence: 99%

See 1 more Smart Citation

RETRACTED: An efficient object detection using OFSA for thermal imaging

Teju

Bhavana

2020

International Journal of Electrical Engineering & Education

View full text Add to dashboard Cite

The demand for identifying a reliable person is increased because of security issues in our daily life. At present, to identify a person biometric technique such as face recognition is introduced. Since,a person with abnormal behaviour recognition system has reached certain level, their accomplishments in real time applications are restricted by challenges, such as illumination variations. The present visual recognition system is good at controlled illumination conditions and thermal face recognition system is better for detecting disguised persons or when there is no illumination control. Hence, a hybrid system which uses both visual and thermal images for recognising a person is better. The objective of this research is to implement a method which improves the quality of the image by fusing visual and thermal imaging images. Our research methodology has introduced to enhance servo line camera images. Nonlinear image transfer functions were introduced,and the parameters associated with those functions are determined by image statistics for making adaptive algorithms. Next methodswereintroduced for registering the visual images to their consequent thermal images. To get a transformation matrix for the registration, the landmarks in the images are first detected and a subset of those landmarks were selected to obtain the matrix, we propose a hybrid algorithm for detection, tracking and classification using OFSA algorithm to fuse the registered thermal and visual images. In this research, we focus on object detection using OFSA algorithm for more accuracy.

show abstract

Section: Teju and Bhavanamentioning

confidence: 99%

“…19 Dynamic adaption of combination method is found as it works simultaneously in day/night and similarly will do the required changes. 19 There are 3 fusion methods. First method is augmenting the GMM design with thermal data in before to foreground segmentation.…”

Section: Teju and Bhavanamentioning

confidence: 99%

RETRACTED: An efficient object detection using OFSA for thermal imaging

Teju

Bhavana

2020

International Journal of Electrical Engineering & Education

View full text Add to dashboard Cite

show abstract

“…The authors have shown that the energy harvester together with a heterogeneous combination of sensors provide better battery life for the camera node. Mouts et al 16 evaluated moving object detection techniques by using a pixel-based statistical approach. The proposed camera system uses a CMOS sensor with a sensitivity from 350 to 1080 nm integrating narrow-band light-emitting diodes (LEDs) to create 17 different spectral bands, ranging from 450 to 990 nm.…”

Section: Related Workmentioning

confidence: 99%

Exploration of preprocessing architectures for field-programmable gate array-based thermal-visual smart camera

Imran

Rinner

Zand

et al. 2016

J. Electron. Imaging

View full text Add to dashboard Cite

Nils, "Exploration of preprocessing architectures for field-programmable gate array-based thermal-visual smart camera," Abstract. Embedded smart cameras are gaining in popularity for a number of real-time outdoor surveillance applications. However, there are still challenges, i.e., computational latency, variation in illumination, and occlusion. To solve these challenges, multimodal systems, integrating multiple imagers can be utilized. However, trade-off is more stringent requirements on processing and communication for embedded platforms. To meet these challenges, we investigated two low-complexity and high-performance preprocessing architectures for a multiple imagers' node on a field-programmable gate array (FPGA). In the proposed architectures, majority of the tasks are performed on the thermal images because of the lower spatial resolution. Analysis with different sets of images show that the system with proposed architectures offers better detection performance and can reduce output data from 1.7 to 99 times as compared with full-size images. The proposed architectures can achieve a frame rate of 53 fps, logics utilization from 2.1% to 4.1%, memory consumption 987 to 148 KB and power consumption in the range of 141 to 163 mW on Artix-7 FPGA. This concludes that the proposed architectures offer reduced design complexity and lower processing and communication requirements while retaining the configurability of the system.

show abstract

“…Tarek et al [2] proposed a background subtraction technique by combining thermal and visible imagery using Gaussian mixture models (GMM). However, the experiments are performed on high-end offline computers.…”

Section: Related Workmentioning

confidence: 99%

“…The existing background subtraction techniques have mostly been evaluated with respect to visual image sensors [6]. In outdoor surveillance applications, background modelling techniques for visual images are prone to produce false positives because of variation in illumination, the animated background, such as shadows or moving trees, shrubs and electrical wires [2]. These applications require background updating periodically in order to adjust the environmental variables.…”

Section: Introductionmentioning

confidence: 99%

Low complexity FPGA based background subtraction technique for thermal imagery

Imran

O’Nils

Munir

et al. 2015

Proceedings of the 9th International Conference on Distributed Smart Cameras

View full text Add to dashboard Cite

Embedded smart camera systems are gaining popularity for a number of real world surveillance applications. However, there are still challenges, i.e. variation in illumination, shadows, occlusion, and weather conditions while employing the vision algorithms in outdoor environments. For safety-critical surveillance applications, the visual sensors can be complemented with beyond-visual-range sensors. This in turn requires analysis, development and modification of existing imaging techniques. In this work, a low complexity background modelling and subtraction technique has been proposed for thermal imagery. The proposed technique has been implemented on Field Programmable Gate Arrays (FPGAs) after in-depth analysis of different sets of images, characterizing poor signal-to-noise ratio challenges, e.g. motion of high frequency background objects, temperature variation and camera jitter etc. The proposed technique dynamically updates the background on pixel level and requires a single frame storage as opposed to existing techniques. The comparison of this approach with two other approaches show that this approach performs better in different environmental conditions. The proposed technique has been modelled in Register Transfer Logic (RTL) and implementation on the latest FPGAs shows that the design requires less than 1 percent logics, 47 percent block RAMs, and consumes 91 mW power consumption on Artix-7 100T FPGA.

show abstract

Fusion of thermal and visible images for day/night moving objects detection

Cited by 10 publications

References 22 publications

RETRACTED: An efficient object detection using OFSA for thermal imaging

RETRACTED: An efficient object detection using OFSA for thermal imaging

Exploration of preprocessing architectures for field-programmable gate array-based thermal-visual smart camera

Low complexity FPGA based background subtraction technique for thermal imagery

Contact Info

Product

Resources

About