A joint validation study on camera-aided illuminance measurement

Abstract

This joint study conducted in the United States and Japan reviewed existing illuminance measurement methods that use a conventional digital single-lens reflex camera, including (a) per-pixel illuminance calculation using non-fisheye wide-angle lenses, (b) hemispherical projection-based illuminance calculation, (c) the KU method developed by the University of Kansas (KU) and (d) the L-CEPT method developed by the Japanese team for per-pixel illuminance calculation using 180° fisheye lens. Next, laboratory and field measurements were conducted in 32 test scenarios in Kansas and Japan to improve and validate the two similar methods (c) and (d) for per-pixel illuminance calculation and compare them to the simplified method (b) using orthographic projection-based illuminance calculation. Based on the test results, the camera-aided illuminance measurement method could have an error rate of 13.7% ± 15.3% (SD) in all 32 scenarios. Large errors (>25%) were observed in six extremely dynamic gymnasiums with rapidly changing morning sunlight. Alternatively, an average error rate of 7.7% ± 7.5% was observed in the 26 test scenarios without rapidly changing direct sunlight. The simplified orthographic projection-based method could achieve the same level of accuracy as the per-pixel KU/L-CEPT method. Yet, multiple issues on camera-aided illuminance measurement still need further investigation.