Plane sweep method for optimal line fitting in track-before-detect

Abstract

The Hough transfonn line detection method has been estab lished as a viable technique for track-before-detect (TBD). However, its basic operation of binning and accumulating votes in the parameter space is computationally expensive. A more critical weakness of Hough transform is its dependence on parameter tuning (e.g., bin size and various thresholds), which can be non-intuitive and data-dependent. This leads to low detection rates in data with low signal-to-noise ratio and significant clutter. In this paper we propose a line detection algorithm with guaranteed global optimality for TBD. Our algorithm is based on the plane sweep algorithm for robust linear regression, with novel modifications to ensure its appli cability under the TBD setting. Unlike the Hough transform, our algorithm has only one parameter to set (essentially the sensor false alarm rate) and can deterministically find the best solution according to a well-defined criterion. Simula tion results on multi-dimensional TBD problems validate the accuracy and efficiency of our method.

Topological Sweep for Multi-Target Detection of Geostationary Space Objects

“…Also under linear trajectory assumption, Guo and White [18] applied random sample consensus (RANSAC) [19] and plane sweep [20] to perform TBD on point-wise measurements. They showed higher accuracy and stability than HT; however, their technique has been demonstrated only on single-target scenarios and synthetic data.…”

“…They showed higher accuracy and stability than HT; however, their technique has been demonstrated only on single-target scenarios and synthetic data. Our approach is inspired by [18], specifically, the usage of computational geometry techniques based on the concept of duality. However, we extend [18] to the multi-target case, improve their runtime using topological sweep [12], and validate our method on real data from SSA.…”

“…Our approach is inspired by [18], specifically, the usage of computational geometry techniques based on the concept of duality. However, we extend [18] to the multi-target case, improve their runtime using topological sweep [12], and validate our method on real data from SSA.…”

“…As another baseline for the proposed method, plane sweep (PS) [18] was used in place of topological sweep in Algorithm 3. Note that PS returns exactly the same results as TS, hence this was mainly for runtime comparisons.…”