<p>Building detection from satellite images is a demanding task and also considered as a hot research topic over the past few years. Deep Learning-based models are applied for object detection. One of the biggest challenges in the Deep Learning-based models learning is the selection of parameter and optimization process. Also numerous models have been proposed using bio-inspired optimization solutions to solve this problem. In this work, to avoid local optima and ensuring a smooth balance of exploration and exploitation involved in building detection, a method called, Secant Deep Belief Network-based Hyperbolic Cosine Whale Optimization (SDBN-HCWO) is proposed. The bio-inspired Hyperbolic Cosine Whale Optimization processes works under the Secant Deep Belief Network. The Secant Deep Belief Network consists of visible and hidden layer. Three hidden layers are employed to detect best edges. In the first hidden layer, Hyperbolic Cosine Prey Encircling is employed to find best edges. The detected edges are linked in second hidden layer with the aid of Shrinking Encircle and Spiral Update-based optimal edge linking model. Lastly, Secant Object Detection model is applied in third hidden layer to perform the robust building detection in an accurate way. The performance of the SDBN-HCWO method is evaluated quantitatively and qualitatively based on the best fitness values. The experimental outcomes of proposed SDBN-HCWO method yields better performance results in terms of higher peak signal-to-noise ratio by 18%, classification accuracy by 20% and reduced classification time by 26% and false positive rate by 68% than the other state-of-the-art methods.</p>