MSCM-LiFe: Multi-scale cross modal linear feature for horizon detection in maritime images

Prasad, Dilip K.; Rajan, Dinesh; Prasath, Chandrashekar Krishna; Rachmawati, Lily; Rajabally, Eshan; Quek, Chai

doi:10.1109/tencon.2016.7848237

Cited by 27 publications

(28 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, using a set of training images and machine learning techniques, features representing horizon were learnt directly. Recent algorithms have combined multi-scale filtering and projection based approaches for providing state-of-the-art results [61], [62]. 4) Comparison of methods for horizon detection: A qualitative comparison of the methods is provided in Table III.…”

Section: ) Region Based Horizon Detectionmentioning

confidence: 99%

Video Processing From Electro-Optical Sensors for Object Detection and Tracking in a Maritime Environment: A Survey

Prasad

Rajan

Rachmawati³

et al. 2017

IEEE Trans. Intell. Transport. Syst.

Self Cite

310

168

View full text Add to dashboard Cite

We present a survey on maritime object detection and tracking approaches, which are essential for the development of a navigational system for autonomous ships. The electro-optical (EO) sensor considered here is a video camera that operates in the visible or the infrared spectra, which conventionally complement radar and sonar and have demonstrated effectiveness for situational awareness at sea has demonstrated its effectiveness over the last few years. This paper provides a comprehensive overview of various approaches of video processing for object detection and tracking in the maritime environment. We follow an approachbased taxonomy wherein the advantages and limitations of each approach are compared. The object detection system consists of the following modules: horizon detection, static background subtraction and foreground segmentation. Each of these has been studied extensively in maritime situations and has been shown to be challenging due to the presence of background motion especially due to waves and wakes. The main processes involved in object tracking include video frame registration, dynamic background subtraction, and the object tracking algorithm itself. The challenges for robust tracking arise due to camera motion, dynamic background and low contrast of tracked object, possibly due to environmental degradation. The survey also discusses multisensor approaches and commercial maritime systems that use EO sensors. The survey also highlights methods from computer vision research which hold promise to perform well in maritime EO data processing. Performance of several maritime and computer vision techniques is evaluated on newly proposed Singapore Marine Dataset.• the difficulty in modeling the dynamics of water (including waves, wakes and foams) for background subtraction and detection of foreground objects, • variations in object appearances due to distance and angle of viewing, and • changes in illumination and weather conditions, such as due to clouds, sunshine, rain, glint, etc.

show abstract

Section: ) Region Based Horizon Detectionmentioning

confidence: 99%

Video Processing From Electro-Optical Sensors for Object Detection and Tracking in a Maritime Environment: A Survey

Prasad

Rajan

Rachmawati³

et al. 2017

IEEE Trans. Intell. Transport. Syst.

Self Cite

310

168

View full text Add to dashboard Cite

show abstract

“…As the marine vehicles in long range always appear near the horizon, the target search area can be limited to the sea sky region [10][11][12][13][14][15]. It can not only greatly reduce the computational cost for searching targets, but also decrease the disturbance brought by illumination changes from sea waves or cloud clutters.…”

Section: оVerview Of Methods For Detecting Horizonmentioning

confidence: 99%

“…The horizon is also used to make image registration for subsequent target tracking [10; 14]. There exist several mainstream algorithms for horizon detection and evaluation such as: color-based statistical model [10; 13; 15], edge phase encoding [12], pixels classification [16], linear feature [10; 12-14], color intensity and gradient [12; 14; 16], textural feature [17], region-growing [19] and other physical characteristics near the horizon [14; 17; 19]. In general, the hybrid algorithm performs a higher accuracy rate but it also brings computational burden.…”

Section: оVerview Of Methods For Detecting Horizonmentioning

confidence: 99%

Method of the horizon detection from electro-optical sensors under maritime environment

Євсеєв¹,

Shmatko²,

Дун³

et al. 2018

СОІ

View full text Add to dashboard Cite

A new method is presented to detect the sea sky line. In the first step, the original image is transformed into grayscale image and the sea-skyline region is located by using the textural features gray-level co-occurrence matrix based on texture feature. In the second step, the adaptive segmentation thresholds are obtained by the OTSU algorithm, which produces a set of sea sky line candidate points. Finally, a simple clustering method is adopted to select appropriate points and transform them by straight line fitting. The results of experiments established on realworld sea-sky images demonstrate the effectiveness and robustness of the proposed approach.

show abstract

“…We search all over of the set S to find the maximum value in their corresponding accumulators. Suppose that the value of [2]; the method adopting probability distribution functions of sea and sky region (H-PDF) [3] and the method by multi-scale cross modal linear feature (MSCM) [9]. The video sequences can be classified into two categories: the camera mounted on board and with camera mounted on shore horizon.…”

Section: Validationmentioning

confidence: 99%

“…Luo et al [7][8] designed a model composed of color classification and physical-motivated signature validation, which is only effective under specific circumstance with clear and light-blue sky at daytime. Dilip et al [9] proposed an algorithm for seasky line detection called multi-scale cross modal linear feature. By multi-scale media filtering, the linear feature is extracted by Hough transform and the intensity variation over different scales.…”

Section: Introductionmentioning

confidence: 99%

An Algorithm for Sea-Sky Line Detection Under Visible Sea Image

Shmatko

Aleksiyev

Liang

2018

A.I.S.

View full text Add to dashboard Cite

Subject of research is the process of sea-sky line detection, based on color feature. The purpose of this work is to develop the method is based on color feature as well as textural information. It consists of sea sky region extraction and horizon detection, which is more precise and fast no matter in the sceneries created by camera mounted on board or on shore. The tasks to be solved is: to propose the new linear fitting metric in sea-sky line extraction. The following results were obtained. The proposed linear fitting method was studies. The performance of proposed horizon detection method is estimated by comparison to other 3 state-of-art methods based on 13 challenging testing videos under different circumstances. The 3 methods are: the method based on discriminates and eigenvalues of covariance matrices in RGB space (H-DE); the method adopting probability distribution functions of sea and sky region (H-PDF) and the method by multi-scale cross modal linear feature (MSCM). The video sequences can be classified into two categories: the camera mounted on board and with camera mounted on shore horizon. Conclusion. The proposed linear fitting method can rectify the outlier values. The experimental results on a sequence of test videos demonstrate that the proposed sea-sky line detection method has a higher accuracy and it is more robust and efficient than other existed methods. K e ywor d s : Sea-sky line; extract the sea-sky line accurately even from low-resolution image; novel horizon detection method for maritime environment.

show abstract

MSCM-LiFe: Multi-scale cross modal linear feature for horizon detection in maritime images

Cited by 27 publications

References 20 publications

Video Processing From Electro-Optical Sensors for Object Detection and Tracking in a Maritime Environment: A Survey

Video Processing From Electro-Optical Sensors for Object Detection and Tracking in a Maritime Environment: A Survey

Method of the horizon detection from electro-optical sensors under maritime environment

An Algorithm for Sea-Sky Line Detection Under Visible Sea Image

Contact Info

Product

Resources

About