Segmentation of Environmental Time Lapse Image Sequences for the Determination of Shore Lines Captured by Hand-Held Smartphone Cameras

Abstract

ABSTRACT:The relevance of globally environmental issues gains importance since the last years with still rising trends. Especially disastrous floods may cause in serious damage within very short times. Although conventional gauging stations provide reliable information about prevailing water levels, they are highly cost-intensive and thus just sparsely installed. Smartphones with inbuilt cameras, powerful processing units and low-cost positioning systems seem to be very suitable wide-spread measurement devices that could be used for geo-crowdsourcing purposes. Thus, we aim for the development of a versatile mobile water level measurement system to establish a densified hydrological network of water levels with high spatial and temporal resolution. This paper addresses a key issue of the entire system: the detection of running water shore lines in smartphone images. Flowing water never appears equally in closerange images even if the extrinsics remain unchanged. Its non-rigid behavior impedes the use of good practices for image segmentation as a prerequisite for water line detection. Consequently, we use a hand-held time lapse image sequence instead of a single image that provides the time component to determine a spatio-temporal texture image. Using a region growing concept, the texture is analyzed for immutable shore and dynamic water areas. Finally, the prevalent shore line is examined by the resultant shapes. For method validation, various study areas are observed from several distances covering urban and rural flowing waters with different characteristics. Future work provides a transformation of the water line into object space by image-to-geometry intersection.

Automatic Image‐Based Water Stage Measurement for Long‐Term Observations in Ungauged Catchments

“…Using the coregistered image sequence, water lines are detectable by their spatio‐temporal texture that has been introduced by Kröhnert and Meichsner (). It is assumed that moving water results in significant changes of the pixel content in the image sequence, whereas river banks remain identical.…”

Subaquatic Digital Elevation Models From Uav-Imagery

“…Furthermore, underwater control points should be installed in order to stabilize the orientation. The shoreline in the images might be extracted automatically by analysing the colour-changes (Kröhnert, et al,2017), (Mulsow et al, 2014b). To refine the water-land transition of the generated DTM Initial values for the shore line can be derived by intersecting the DTM with the plane water-level, as already shown.…”

Photogrammetric water level determination using smartphone technology

“… Time‐lapse image acquisition, processing and 2D water‐line detection (see Kröhnert and Meichsner, , for more details about the implementation). Determination of the initial camera exterior orientation using smartphone sensors. Collecting metadata information about the smartphone camera, that is approximate values of the camera interior orientation and the acquisition time to support the selection of convenient 3D data, referring to season and time of day. …”

“…With regards to step 1 (image acquisition and 2D water‐line detection), the reader is referred to Kröhnert and Meichsner (), which should be considered as an integral part of the proposed workflow. In a nutshell, short time‐lapse image sequences of a target river section are used to distinguish a static shore area from a dynamic river area, which provides information about the water line.…”