Remote sensing images often exhibit lower contrast than usual. Contrast Limited Adaptive Histogram Equalization (CLAHE) is a well-established and robust local contrast enhancement algorithm, renowned for its high-quality results, particularly in the medical domain. In this article, we introduce an automated contrast-limit adaptive histogram equalization method applied on remote sensing images, drawing inspiration from CLAHE. Our proposed algorithm incorporates automatic outlier detection blocks into the standard CLAHE framework, addressing the limitation of relying on a predetermined single clip-limit as is preset in traditional CLAHE. Instead, our approach adapts multiple clip-limits, one for each Contextual Region (CR), rather than a global clip-limit used in the original algorithm. First, the algorithm divides the image into tiles based on proximity, called contextual region, then it computes the histogram for each CR. In this stage, the CLAHE depends on clip-limit as pre-set user input to clip the intensities above clip-limit, then it redistributes the deducted intensities over the quantization range. On the contrary, the proposed algorithm calculates outliers of each CR and considers a clip-limit for the CR. Next, histogram equalization is performed on the modified CR histogram. Finally, Image is reconstructed by applying bilinear interpolation to outcome CRs. Experimental and comparison results showed that the proposed technique provides better results than classic CLAHE for remote sensing images on DOTA dataset. Moreover, the proposed algorithm achieves an improvement of 27.960 for PSNR and 3.271 for CG.