Impact of selecting image feature detection method for development of panorama under different light conditions
Venkat P. Patil, Umakant B. Gohatre · 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI) · 2017
Photographic Image mosaicing is the technique in which multiple photographic images are taken from same scene and combined together to form a panorama to get a high resolution image. In this process multiple photographic images are overlapped and process of blending is applied to form a wide angle or broad view panoramic image. The main important steps consist of firstly image acquisition of a scene then image registration and lastly image blending. The image registration method used in this paper is based on a feature based method for feature detection. Comparison of different photographic image feature detectors and descriptors and evaluating their basic performance is very important in study of image processing and computer vision. In this paper, the performance evaluation is done to compare three combinations of well-known methods of image feature detectors and descriptors which are SIFT, SURF and ORB for different light conditions. Upon inspecting the obtained results, it is observed that the ORB can be preferable almost in the situations of daylight conditions and for night light SURF is preferable.