Extracting targets from regions-of-interest in infrared images using a 2-D histogram

Park, Chan Woo; Lee, Jong Min; Kim, Yong Min; Kim, Yong; Song, Taek Lyul; Park, Ki Tae; Moon, Young Shik

doi:10.1117/1.3536471

Cited by 5 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the thresholding-based methods, each pixel of infrared image is considered as two-class (background class and ship target class) division problem and is discriminated with an optimal threshold by fully considering the gray intensity distribution of infrared ship image. The well-known two-dimensional (2-D) Otsu [10] and 2-D maximum entropy [11], [12] were used to find the optimal segmentation threshold by transferring the IR ship image into the 2-D histogram. Zhang and Wu et al [13], [14] employed Canny operator to locate sea-sky line, and presented a recursive Otsu segmentation method including global Otsu and local Otsu to extract ship targets.…”

Section: Related Workmentioning

confidence: 99%

“…tail wave, reflective clutter and backlit clutter). Accordingly, the intensity-based ship target segmentation methods [10], [12], [16] will introduce those uneven parts into the segmentation result and cause under-segmentation. Furthermore, by staring at the appearance model of ship target in IR image, the existing methods commonly assume that the ship target is the uniform region against the sea background [22], [25], [26].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Infrared Ship Target Segmentation Based on Structure Tensor and Maximum Histogram Entropy

Ding³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The existing infrared (IR) ship target segmentation methods may suffer serious performance degradation in the situation of diverse background clutters and ship targets. To cope with this problem, a novel ship target segmentation method is proposed in this paper. Initially, the IR image is transformed into the map of large eigenvalues of structure tensor (STLE), where the horizon line and ship target boundary can be explicitly characterized. According to the scene context clue, the automatic horizon line detection (AHLD) is proposed to efficiently judge the existence of horizon line and remove sky/land region clutters. Then, based on the intensity distribution of ship target and sea background, the adaptive maximum histogram entropy (AMHE) is presented to accurately perceive the brightness (dark or bright) of ship target, and coarsely segment the bright or dark ship target from sea background. After that, considering the ship target boundary information, the regions-of-interest (ROI) of ship target is located and the ship foreground map (SFM) is developed to address the under-segmentation. Finally, a new Watershed algorithm namely structure tensor and maximum histogram entropy modified Watershed transform (TEWT) is constructed to completely extract the whole ship target. Extensive experiments show that the proposed method outperforms the state-of-the-art methods, especially for IR images with intricate background clutter and heavy noise. Moreover, the proposed method can work stably for ship target with unknown brightness, uneven intensities, low contrast, variable quantities, sizes, and shapes.INDEX TERMS Infrared (IR) imaging, ship target segmentation, structure tensor, maximum histogram entropy, modified watershed transform.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic Infrared Ship Target Segmentation Based on Structure Tensor and Maximum Histogram Entropy

Ding³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…[1][2][3][4] Khabou and Gader 4 proposed an automatic target recognition technique using entropy optimized shared-weight neural networks. Over the last two decades, several statistical-and artificial intelligence-based detection techniques have been investigated.…”

Section: Introductionmentioning

confidence: 99%

Detection of reappearing targets in forward-looking infrared video sequences

Alam

Bal

2015

Opt. Eng

View full text Add to dashboard Cite

Often sensor ego-motion or fast target movement causes the target to temporarily go out of the fieldof-view leading to reappearing target detection problem in target tracking applications. Since the target goes out of the current frame and re-enters at a later frame, the re-entering location and variations in rotation, scale, and other three-dimensional orientations of the target are not known, thus complicating the detection and tracking of reappearing targets. A new training-based target detection algorithm has been developed using tuned basis functions (TBFs). The detection algorithm uses target and background information, extracted from training samples, to detect possible candidate target images. The detected candidate target images are then introduced into the second algorithm, called clutter rejection module, to determine the target re-entering frame and location of the target. The second algorithm has been designed using the spatial domain correlation-based template matching (TM) technique. If the target re-enters the current frame, the target coordinates are detected and tracking algorithm is initiated. The performance of the proposed TBF-TM-based reappearing target detection algorithm has been tested using real-world forward-looking infrared video sequences.Alam and Bal: Detection of reappearing targets in forward-looking infrared video sequences Downloaded From: http://opticalengineering.spiedigitallibrary.org/ on 08/19/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx

show abstract

“…표적을 포함하는 관심영역(Region of Interest, ROI)이 One-bit 변환에 의하여 추출된 연구가 [7]에서 수행되었고, [8]에서는 수평, 수직 투영모델에 의한 가우시안 혼합분포를 기반으로 한 적외선 영상 분할이 연구되었다. 또한, [9]에서는 표적의 위치와 화소 값을 모델링하는 2차원 히스토그램 방법이 제안되었다. 다단계 영상 분할 방법으로 적외선 영상의 표적을 분할한 연구가 [10,11]에서 수행되었고, [12,13] 에서는 ROI를 추출하고 개별적인 ROI에 EM 또는 다단계(Multi- (Fig.…”

unclassified

Infrared Image Segmentation by Extracting and Merging Region of Interest

Yeom¹

2016

Journal of Korean Institute of Intelligent Systems

View full text Add to dashboard Cite

Infrared (IR) imaging is capable of detecting targets that are not visible at night, thus it has been widely used for the security and defense system. However, the quality of the IR image is often degraded by low resolution and noise corruption. This paper addresses target segmentation with the IR image. Multiple regions of interest (ROI) are extracted by the multi-level segmentation and targets are segmented from the individual ROI. Each level of the multi-level segmentation is composed of a k-means clustering algorithm an expectation-maximization (EM) algorithm, and a decision process. The k-means clustering algorithm initializes the parameters of the Gaussian mixture model (GMM) and the EM algorithm iteratively estimates those parameters. Each pixel is assigned to one of clusters during the decision. This paper proposes the selection and the merging of the extracted ROIs. ROI regions are selectively merged in order to include the overlapped ROI windows. In the experiments, the proposed method is tested on an IR image capturing two pedestrians at night. The performance is compared with conventional methods showing that the proposed method outperforms others.

show abstract

Extracting targets from regions-of-interest in infrared images using a 2-D histogram

Cited by 5 publications

References 15 publications

Automatic Infrared Ship Target Segmentation Based on Structure Tensor and Maximum Histogram Entropy

Automatic Infrared Ship Target Segmentation Based on Structure Tensor and Maximum Histogram Entropy

Detection of reappearing targets in forward-looking infrared video sequences

Infrared Image Segmentation by Extracting and Merging Region of Interest

Contact Info

Product

Resources

About