Object Detection Using Hausdorff Distance and Multiclass Discriminative Field

نویسندگان

  • Xiaofeng Zhang
  • Hong Ding
  • Rengui Cheng
چکیده

In this paper, we present a novel object detection scheme using only local contour fragments. A sample fragment extraction method decomposes a whole contour into several parts. Then, the candidate locations of corresponding fragments in test images are detected by a modified Hausdorff distance with punishment on clutter edge regions. The most probable locations are selected by Multiclass Discriminative Field (MDF). Finally, contours of the objects can be drawn with these locations and sample fragments. Our major contributions are simplifying the MDF by an undirected graph constructed by the candidate locations and directly selecting the fragment locations by this MDF. The results on our postmark database and the ETHZ database from internet show that the proposed scheme is practicable.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Object Detection Using Contour Fragments

In this paper, we present a novel object detection scheme using contour fragments. The template fragments are extracted by decomposing the template contour. The hinge angle, contour direction and partial Hausdorff distance (PHD) are used to match the fragments in the edge image. Then, the Multiclass Discriminative Field (MDF) is used to select the matches. With these selected matches and their ...

متن کامل

Object Detection Based on Multi-scale Contour Fragments

In this paper, we present a novel object detection scheme using the multi-scale contour fragments. The template fragments are extracted by decomposing the template contour. The multi-scale hinge angle, contour direction and partial Hausdorff distance (PHD) are used to select candidates in the edge image. Then, the matches with different scales and directions are selected by the Multiclass Discr...

متن کامل

Multiclass Discriminative Fields for Parts-Based Object Detection

In this paper, we present a discriminative framework for parts-based object detection based on the multiclass extensions of binary discriminative fields described in [1]. These fields allow simultaneous discriminative modeling of the appearance of individual parts and the geometric relationship between them. The conventional Markov Random Field (MRF) formulations cannot be used for this purpose...

متن کامل

Object Detection and Segmentation using Discriminative Learning

Jingdan Zhang: Object Detection and Segmentation using Discriminative Learning. (Under the direction of Leonard McMillan.) Object detection and segmentation algorithms need to use prior knowledge of objects’ shape and appearance to guide solutions to correct ones. A promising way of obtaining prior knowledge is to learn it directly from expert annotations by using machine learning techniques. P...

متن کامل

GPU-based Collision Detection and Response for Particles on 3D Models

This paper presents a GPU-based approach to handle collision detection and response for particles on 3D models. Signed Hausdorff distance fields were used and stored in volume textures. The voxels in a distance field stored the Hausdorff distance to the 3D model and the normal of the corresponding nearest surface. Object-based collision detection and response were processed using a pixel shader...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2013