Based on deep learning, one method for the intelligent detection of parking spaces is proposed. The TensorFlow deep learning platform is applied to train the car object recognition model, the optimal interval of the effective car images is extracted, the accurate recognition result of the car distribution is presented, and the order numbering of the recognition results of the car distribution and the accurate judgment of the vacancy situation of parking spaces are realized. The simulation results and the actually collected data are adopted to verify the reliability of intelligent identification of parking space distribution, intelligent numbering of parking space, and the judgement of empty parking space.