CAE-RLSM: Consistent and Efficient Redundant Line Segment Merging for Online Feature Map Building
نویسندگان
چکیده
منابع مشابه
Building Efficient ConvNets using Redundant Feature Pruning
This paper presents an efficient technique to prune deep and/or wide convolutional neural network models by eliminating redundant features (or filters). Previous studies have shown that over-sized deep neural network models tend to produce a lot of redundant features that are either shifted version of one another or are very similar and show little or no variations; thus resulting in filtering ...
متن کاملLSM: perceptually accurate line segment merging
Existing line segment detectors tend to break up perceptually distinct line segments into multiple segments. We propose an algorithm for merging such broken segments to recover the original perceptually accurate line segments. The algorithm proceeds by grouping line segments on the basis of angular and spatial proximity. Then those line segment pairs within each group that satisfy unique, adapt...
متن کاملConsistent and Efficient Nonparametric Different-Feature Selection
The proposed method can be interpreted as a generalization of our previous method [1], which is the first algorithm that uses the sparsest k-subgraph problem for different-feature selection. Unlike the proposed method, the previous method has limited applicability due to the Gaussian assumption. In the previous method, we assumed Gaussian distributions on p and q, and defined the matrix L̂ by L̂d...
متن کاملWeighted line fitting algorithms for mobile robot map building and efficient data representation
This paper presents an algorithm to find the line-based map that best fits sets of two-dimensional range scan data that are acquired from multiple poses. To construct these maps, we first provide an accurate means to fit a line segment to a set of uncertain points via a maximum likelihood formalism. This scheme weights each point’s influence on the fit according to its uncertainty, which is der...
متن کاملA Feature Representation for Map Building and Path Planning
We explain how most conventional approaches to the problem of visually guided robot navigation are fundamentally restricted. Starting with a specification of the requirements of a general purpose visually guided robot which includes, robustness, autonomy, flexibility and scalability, we then develop an approach to the solution of map building and path planning which operates within a learning f...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Instrumentation and Measurement
سال: 2020
ISSN: 0018-9456,1557-9662
DOI: 10.1109/tim.2019.2949318