MixedPeds: Pedestrian Detection in Unannotated Videos using Synthetically Generated Human-agents for Training
This addresses the challenge of reducing annotation costs for pedestrian detection in videos, though it is incremental as it builds on existing synthetic data methods.
The paper tackles the problem of training pedestrian detectors without manual annotations by creating a mixed reality dataset with synthetic human-agents placed in real-world images, using a novel Spawn Probability Map for appropriate placement. The result is an improvement in average precision by 5-13% over detectors trained on manually labeled datasets.
We present a new method for training pedestrian detectors on an unannotated set of images. We produce a mixed reality dataset that is composed of real-world background images and synthetically generated static human-agents. Our approach is general, robust, and makes no other assumptions about the unannotated dataset regarding the number or location of pedestrians. We automatically extract from the dataset: i) the vanishing point to calibrate the virtual camera, and ii) the pedestrians' scales to generate a Spawn Probability Map, which is a novel concept that guides our algorithm to place the pedestrians at appropriate locations. After putting synthetic human-agents in the unannotated images, we use these augmented images to train a Pedestrian Detector, with the annotations generated along with the synthetic agents. We conducted our experiments using Faster R-CNN by comparing the detection results on the unannotated dataset performed by the detector trained using our approach and detectors trained with other manually labeled datasets. We showed that our approach improves the average precision by 5-13% over these detectors.