An Elastic Deformation Field Model for Object Detection and Tracking

Abstract

Deformable Parts Models (DPM) are the current stateof-the-art for object detection. Nevertheless they seem sub-optimal in the representation of deformations. Object deformations are often continuous and not confined to big parts. Therefore we propose to replace the DPM star model based on big parts by a deformation field. This consists of a grid of small parts connected with pairwise constraints which can better handle continuous deformations. The naive application of this model for object detection would consist of a bounded sliding window approach: for each possible location of the image the best part configuration within a limited bound around this location is found. This is computationally very expensive. Instead, we propose a different inference procedure, where an iterative image-level search finds the best object hypothesis. We show that this approach is faster than bounded sliding windows yet produces comparable accuracy. Experiments further show that the deformation field can better approximate real object deformations and therefore, for certain classes, produces even better detection accuracy than state-of-the-art DPM. Finally, the same approach is adapted to model-free tracking, showing improved accuracy also in this case.

Using a Deformation Field Model for Localizing Faces and Facial Points under Weak Supervision

“…We build our model on the deformation field model (DFM) proposed for object detection in [18]. In this section we first revise the DFM and then we show how to adapt it to detecting faces.…”

“…Instead, we consider the problem as an instance of a CRF optimization where nodes are the object parts, node labels are the locations of the parts in an image and edges are the pairwise connections between parts. As proposed in [18] for each mixture and for each scale we globally maximize Eq. (1) using alpha expansion [1], which is fast.…”

“…The computational cost of the algorithm is linear in the number of locations in the image and it is empirically linear also in the number of parts. For a complete analysis of speed and quality of this deformation model we refer to [18].…”

“…Unfortunately, the alpha expansion algorithm puts only a weak bound on the quality of the solution [1]. As suggested in [18], to keep the convergence, we maintain a buffer with the previously assigned values for the latent variables. When the new assignment is effectuated, we maintain it only if it produces a lower loss (higher score); otherwise the old assignment is restored.…”

“…This deformation model has loops and therefore its optimization is in general too expensive for detection. However, the inference procedure proposed in [18] makes the detection computationally feasible for up to 100 object parts. This model is well suited for perspective-like deformations and is general enough to automatically and jointly learn the face appearance, align the faces and learn the pairwise deformation costs without any facial point annotation.…”