Limits...
Robust pedestrian detection by combining visible and thermal infrared cameras.

Lee JH, Choi JS, Jeon ES, Kim YG, Le TT, Shin KY, Lee HC, Park KR - Sensors (Basel) (2015)

Bottom Line: Our research is novel, compared to previous works, in the following four ways: First, we implement the dual camera system where the axes of visible light and thermal cameras are parallel in the horizontal direction.The final areas of pedestrians are located by combining the detected positions of the CWI and CSI of the thermal image based on OR operation.Experimental results showed that the average precision and recall of detecting pedestrians are 98.13% and 88.98%, respectively.

View Article: PubMed Central - PubMed

Affiliation: Division of Electronics and Electrical Engineering, Dongguk University, 26 Pil-dong 3-ga, Jung-gu, Seoul 100-715, Korea. easygns@dgu.edu.

ABSTRACT
With the development of intelligent surveillance systems, the need for accurate detection of pedestrians by cameras has increased. However, most of the previous studies use a single camera system, either a visible light or thermal camera, and their performances are affected by various factors such as shadow, illumination change, occlusion, and higher background temperatures. To overcome these problems, we propose a new method of detecting pedestrians using a dual camera system that combines visible light and thermal cameras, which are robust in various outdoor environments such as mornings, afternoons, night and rainy days. Our research is novel, compared to previous works, in the following four ways: First, we implement the dual camera system where the axes of visible light and thermal cameras are parallel in the horizontal direction. We obtain a geometric transform matrix that represents the relationship between these two camera axes. Second, two background images for visible light and thermal cameras are adaptively updated based on the pixel difference between an input thermal and pre-stored thermal background images. Third, by background subtraction of thermal image considering the temperature characteristics of background and size filtering with morphological operation, the candidates from whole image (CWI) in the thermal image is obtained. The positions of CWI (obtained by background subtraction and the procedures of shadow removal, morphological operation, size filtering, and filtering of the ratio of height to width) in the visible light image are projected on those in the thermal image by using the geometric transform matrix, and the searching regions for pedestrians are defined in the thermal image. Fourth, within these searching regions, the candidates from the searching image region (CSI) of pedestrians in the thermal image are detected. The final areas of pedestrians are located by combining the detected positions of the CWI and CSI of the thermal image based on OR operation. Experimental results showed that the average precision and recall of detecting pedestrians are 98.13% and 88.98%, respectively.

No MeSH data available.


Related in: MedlinePlus

The results of background subtraction by our method and previous one [37]. Upper and lower figures of (a,b) are the results with the visible light and thermal images, respectively: (a) Results by our method; (b) Results by previous method [37].
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4481953&req=5

sensors-15-10580-f014: The results of background subtraction by our method and previous one [37]. Upper and lower figures of (a,b) are the results with the visible light and thermal images, respectively: (a) Results by our method; (b) Results by previous method [37].

Mentions: In addition, we compared the background subtraction by our method with that based on Gaussian background-subtraction approach which has been widely used [37]. For fair comparisons, only the background update and subtraction (Steps (1)–(5) and (7)–(9) of Figure 3) are replaced by [37] when measuring the performance by previous method [37]. Because their method can be applied to both the visible light and thermal images, we compared the performances by our method in visible light (Table 5) and thermal image (Table 6) and those by their method. Figure 14 shows the results of background subtraction by our method and previous one [37]. As shown in this figure, we can find that our background subtraction method outperforms the previous one [37].


Robust pedestrian detection by combining visible and thermal infrared cameras.

Lee JH, Choi JS, Jeon ES, Kim YG, Le TT, Shin KY, Lee HC, Park KR - Sensors (Basel) (2015)

The results of background subtraction by our method and previous one [37]. Upper and lower figures of (a,b) are the results with the visible light and thermal images, respectively: (a) Results by our method; (b) Results by previous method [37].
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4481953&req=5

sensors-15-10580-f014: The results of background subtraction by our method and previous one [37]. Upper and lower figures of (a,b) are the results with the visible light and thermal images, respectively: (a) Results by our method; (b) Results by previous method [37].
Mentions: In addition, we compared the background subtraction by our method with that based on Gaussian background-subtraction approach which has been widely used [37]. For fair comparisons, only the background update and subtraction (Steps (1)–(5) and (7)–(9) of Figure 3) are replaced by [37] when measuring the performance by previous method [37]. Because their method can be applied to both the visible light and thermal images, we compared the performances by our method in visible light (Table 5) and thermal image (Table 6) and those by their method. Figure 14 shows the results of background subtraction by our method and previous one [37]. As shown in this figure, we can find that our background subtraction method outperforms the previous one [37].

Bottom Line: Our research is novel, compared to previous works, in the following four ways: First, we implement the dual camera system where the axes of visible light and thermal cameras are parallel in the horizontal direction.The final areas of pedestrians are located by combining the detected positions of the CWI and CSI of the thermal image based on OR operation.Experimental results showed that the average precision and recall of detecting pedestrians are 98.13% and 88.98%, respectively.

View Article: PubMed Central - PubMed

Affiliation: Division of Electronics and Electrical Engineering, Dongguk University, 26 Pil-dong 3-ga, Jung-gu, Seoul 100-715, Korea. easygns@dgu.edu.

ABSTRACT
With the development of intelligent surveillance systems, the need for accurate detection of pedestrians by cameras has increased. However, most of the previous studies use a single camera system, either a visible light or thermal camera, and their performances are affected by various factors such as shadow, illumination change, occlusion, and higher background temperatures. To overcome these problems, we propose a new method of detecting pedestrians using a dual camera system that combines visible light and thermal cameras, which are robust in various outdoor environments such as mornings, afternoons, night and rainy days. Our research is novel, compared to previous works, in the following four ways: First, we implement the dual camera system where the axes of visible light and thermal cameras are parallel in the horizontal direction. We obtain a geometric transform matrix that represents the relationship between these two camera axes. Second, two background images for visible light and thermal cameras are adaptively updated based on the pixel difference between an input thermal and pre-stored thermal background images. Third, by background subtraction of thermal image considering the temperature characteristics of background and size filtering with morphological operation, the candidates from whole image (CWI) in the thermal image is obtained. The positions of CWI (obtained by background subtraction and the procedures of shadow removal, morphological operation, size filtering, and filtering of the ratio of height to width) in the visible light image are projected on those in the thermal image by using the geometric transform matrix, and the searching regions for pedestrians are defined in the thermal image. Fourth, within these searching regions, the candidates from the searching image region (CSI) of pedestrians in the thermal image are detected. The final areas of pedestrians are located by combining the detected positions of the CWI and CSI of the thermal image based on OR operation. Experimental results showed that the average precision and recall of detecting pedestrians are 98.13% and 88.98%, respectively.

No MeSH data available.


Related in: MedlinePlus