Active Deformable Part Models
This paper presents an active approach for part-based object detection, which optimizes the order of part filter evaluations and the time at which to stop and make a prediction. Statistics, describing the part responses, are learned from training data and are used to formalize the part scheduling problem as an offline optimization. Dynamic programming is applied to obtain a policy, which balances the number of part evaluations with the classification accuracy. During inference, the policy is used as a look-up table to choose the part order and the stopping time based on the observed filter responses. The method is faster than cascade detection with deformable part models (which does not optimize the part order) with negligible loss in accuracy when evaluated on the PASCAL VOC 2007 and 2010 datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
General Classificationobject-detectionObject DetectionSchedulingSimilar Papers 제목 키워드 기반
HMDO: Markerless Multi-view Hand Manipulation Capture with Deformable Objects
We construct the first markerless deformable interaction dataset recording interactive motions of the hands and deformable objects, called HMDO (Hand Manipulation with Deformable Objects). With our built multi-view captu…
ObjectObject ReconstructionPose EstimationUnifying Holistic and Parts-Based Deformable Model Fitting
The construction and fitting of deformable models that capture the degrees of freedom of articulated objects is one of the most popular areas of research in computer vision. The two main approaches are: Holistic Deformab…
Face AlignmentDeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos
World models for deformable objects should recover not only geometry and appearance, but also underlying physical dynamics, interaction grounding, and material behavior. Learning such a model from real videos is challeng…
Underwater Fish Tracking for Moving Cameras based on Deformable Multiple Kernels
Fishery surveys that call for the use of single or multiple underwater cameras have been an emerging technology as a non-extractive mean to estimate the abundance of fish stocks. Tracking live fish in an open aquatic env…
Proprioceptive Safe Active Navigation and Exploration for Planetary Environments
Deformable granular terrains introduce significant locomotion and immobilization risks in planetary exploration and are difficult to detect via remote sensing (e.g., vision). Legged robots can sense terrain properties th…