Efficient Scale and Rotation Invariant Object Detection Based on HOGs and Evolutionary Optimization Techniques

Object detection and localization in an image can be achieved by representing an object as a Histogram of Oriented Gradients (HOG). HOGs have proven to be robust object descriptors. However, to achieve accurate object localization, one must take a sliding window approach and evaluate the similarity of the descriptor over all possible windows in an image. In case that search should also be scale and rotation invariant, the exhaustive consideration of all possible HOG transformations makes the method impractical due to its computational complexity. In this work, we first propose a variant of an existing rotation invariant HOG-like descriptor. We then formulate object detection and localization as an optimization problem that is solved using the Particle Swarm Optimization (PSO) method. A series of experiments demonstrates that the proposed approach results in very large performance gains without sacrificing object detection and localization accuracy.