Boat Speed Monitoring Using Artificial Vision

Abstract

Abstract. This paper describes a method to detect, measure the speed, and extract statistics of boats moving on a wide water surface using a single image stream taken from grayscale camera. The approach is based on a background subtraction technique combined with classification and tracking to improve robustness; it provides a stable detection even with sea waves and strong light reflections. The method returns correct speed values within the range ±5% in the 97% of use cases. The algorithm has been integrated in a speed warning prototype system on the Burano island in Venice, monitoring a 250 m wide channel slice. Images are captured by a high resolution camera and processed on site in real-time. Processing results can be accessed remotely for monitoring purposes. The system has been up and running for more than two years.

Using Conventional Cameras as Sensors for Estimating Confidence Intervals for the Speed of Vessels from Single Images

“…Thus, their covariances were zero, with Λ ϑ being a diagonal matrix and σ θ being the standard deviation of the input variable θ ∈ ϑ. The partial derivatives in ∇ U (10) were taken with respect to the nine variables in ϑ. Appendix A presents the expressions that were used to compute those partial derivatives.…”

“…Otherwise, their method would not have been applicable to most of the images in Table 2. Unfortunately, it was not possible to perform a comparison between our approach and techniques that use image sequences, such as [10,11], because their implementation was not available and the descriptions that are presented in the articles proved to be insufficient for proper reproduction. In any case, such techniques cannot be used for video from cameras that are onboard vessels, which limits the scope of their application.…”

“…Other techniques perform tracking and estimations of speed using image sequences that were taken with a digital camera [10][11][12]. However, video-based techniques require fixed cameras to estimate speed from the relative motion.…”

“…Transport the uncertainty that are propagated on H onto c 1 and c 2 by mapping c 1 and c 2 back to the rectified ROI using:c j = x c j , y c j , Hc j = H x c j , y c j , w c j T .The derivatives of c j , for j ∈ {1, 2}, were:Vessel speed U. By replacing D and λ (7) in (8), U was written in terms of a constant term r that multiplied the square root of the Euclidean distance between points c 1 and c 2 :U = r 4 (x c 2 − x c 1 ) 2 + (y c 2 − y c 1 ) 2 , where r = 1.944 g √ 3 4π.The components of ∇ U(10) were computed as:∂U ∂ϑ = r (x c 1 − x c 2 ) ∂x c 1 ∂ϑ − ∂x c 2 ∂ϑ + (y c 1 − y c 2 ) ∂y c 1 ∂ϑ − ∂y c 2 ∂ϑ 2 (x c 1 − x c 2 ) 2 + (y c 1 − y c 2 ) 2…”

Computing Vessel Velocity from Single Perspective Projection Images

“…Other techniques estimate speed using image sequences taken with a digital camera. Broggi et al [5] describes a method of detecting, measuring speed, and extracting statistics for vessels moving over a wide water surface using images stream taken from a gray-scale camera. They demonstrated stable vessel detection even with sea waves and strong light reflections.…”