Evaluation of state-of-the-art object detection algorithms for the task of pedestrian detection. The algorithms include; Faster-RCNN, RPN+BF, YOLO, and SSD. The evaluation is done using the original models, in addition to fine-tuning these models using the training set of many pedestrian detection datasets. The pedestrian detection datasets used are: Caltech, Daimler, Inria person, ETH, TUD-Brussels, GS-PANKit, and SYNTHIA.