While pedestrian detection is a hot topic in recent years, a lot of scholars have proposed many models whose performance are improved gradually. Meanwhile, there are two issues coming. On the one hand, the algorithm complexity increases rapidly with improving the detection accuracy. On the other hand, in the particular images each model have its advantages. So, a single model is very difficult to adapt to the all condition of all images. If a variety of models are merged simply, there is no doubt that causes the high complexity and dimension disaster. Furthermore, it can’t bring the performance of each model into full play. By introducing the recommender system into pedestrian detection, we propose a adaptive-scenario model-selection method for pedestrian detection. On the training set, we structure the rating matrix by combining the model-task rating and the scenes features, and use the collaborative filtering method to chose the appropriate models. In our experiments, we construct model set with significantly different models which are especially discriminating on the aspect of algorithm complexity. The test results in PASCAL VOC datasets show that the accuracy of our method is a little better than the best performance model in the model set. Meanwhile, the average efficiency is obviously improved by our method due to our recommender system selecting a percentage of the low complexity models. The experiments shows that our proposed recommender system can effectively recommend the suitable detection model from model set. The approach has the same significance for other detection task.