Camera traps generating a huge number of images help to study and monitor the wildlife. However, camera traps work at any time of the day and under any weather conditions. Therefore, many images have low or high illumination, blurring, and other defects. This complicates image analysis by both humans and computer systems. In this study, we develop an adaptive illumination correction algorithm based on a modified Multi-Scale Retinex (MSR). First, we accelerate computation by using recursive implementation of the Gaussian filter and utilizing look-up tables to find logarithms and new brightness values. Second, response of the MSR function is transformed by a modified threshold normalization to improve image quality. The upper and lower thresholds are calculated based on statistical information. Finally, we offer automatic adjustment of parameters depending on the area of the image in order to increase usability. Proposed algorithm was tested with various settings on a set of images obtained from camera traps. Experimental results show a high potential for its application.