Stockpile Monitoring Using Linear Shape-From-Shading on Planetscope Imagery

Abstract

Abstract. The storage and management of stockpiles of materials is a fundamental process in large scale activities such as mining, civil engineering, and in the management of waste landfill sites. Following the evolution of stocks has always been important, and advancements in remote sensing technology are not only facilitating this, but also making it possible in near real-time. Nowadays, this monitoring appears to be performed almost exclusively using UAV based techniques. This paper proposes to apply a simple Shape-from-Shading method on low resolution satellite images provided by PlanetScope to monitor the evolution of the volume of stockpiles. The proposed Shape-from-Shading formulation makes it possible to handle occluding objects in the scene. The loss in accuracy due to the low resolution of PlanetScope images is well compensated by the daily revisit frequency and by the fact that spaceborne acquisitions require no human supervision. With satellites it is also easy to follow simultaneously several stocking sites all over the world. We test our method on two coal storage sites and demonstrate that the stockpiles are well detected.

Interactive Segmentation for Shape From Shading Over HR SAR Images

“…The main site-information is the region of interest, which is the same from image to image and whose determination amounts to a negligible annotation time. This is why it has not been mentioned in previous works [4].…”

“…Remote sensing tools like photography from planes or Unmanned Aerial Vehicles (UAVs) are often preferred to site monitoring [2,3]. Satellite images provide a high revisit time and worldwide coverage [4]. SAR imaging does not require sunlight and is free from the influence of atmospheric conditions.…”

“…To illustrate this approach, we tackle the problem of coal volume estimation from high-resolution SAR imaging. This case has two big differences with the work in [4]: in the current paper the images are higher resolution SAR images and we introduce an interactive segmentation approach to provide mask priors. In this particular problem, coal stockpiles are located near harbors.…”

Automatic Stockpile Volume Monitoring using Multi-view Stereo from SkySat Imagery

“…Most image based approaches to compute stockpile volume perform a 3D reconstruction of the area based on the dense matching of multiple views [1,2,3,5]. Single image methods using site-specific heuristics or shape from shading have also been explored [8].…”

“…However, aerial or ground based solutions are often costly or not viable in restricted areas, which may prevent frequent updates. Recurrent satellite imagery is hence emerging as an alternative, as it allows to classify, segment and reconstruct large areas without on-site actions [5,6,7,8]. Today's abundance of Earth observation satellite images, notably due to the breakthrough of SmallSats, explains this growing trend.…”