Feature Map Filtering: Improving Visual Place Recognition with Convolutional Calibration

by   Stephen Hausler, et al.

Convolutional Neural Networks (CNNs) have recently been shown to excel at performing visual place recognition under changing appearance and viewpoint. Previously, place recognition has been improved by intelligently selecting relevant spatial keypoints within a convolutional layer and also by selecting the optimal layer to use. Rather than extracting features out of a particular layer, or a particular set of spatial keypoints within a layer, we propose the extraction of features using a subset of the channel dimensionality within a layer. Each feature map learns to encode a different set of weights that activate for different visual features within the set of training images. We propose a method of calibrating a CNN-based visual place recognition system, which selects the subset of feature maps that best encodes the visual features that are consistent between two different appearances of the same location. Using just 50 calibration images, all collected at the beginning of the current environment, we demonstrate a significant and consistent recognition improvement across multiple layers for two different neural networks. We evaluate our proposal on three datasets with different types of appearance changes - afternoon to morning, winter to summer and night to day. Additionally, the dimensionality reduction approach improves the computational processing speed of the recognition system.


page 2

page 4

page 6

page 7

page 8

page 9


Filter Early, Match Late: Improving Network-Based Visual Place Recognition

CNNs have excelled at performing place recognition over time, particular...

STA-VPR: Spatio-temporal Alignment for Visual Place Recognition

Recently, the methods based on Convolutional Neural Networks (CNNs) have...

Topological Semantic Mapping by Consolidation of Deep Visual Features

Many works in the recent literature introduce semantic mapping methods t...

Localizing Discriminative Visual Landmarks for Place Recognition

We address the problem of visual place recognition with perceptual chang...

Patch-DrosoNet: Classifying Image Partitions With Fly-Inspired Models For Lightweight Visual Place Recognition

Visual place recognition (VPR) enables autonomous systems to localize th...

Adversarial Training for Adverse Conditions: Robust Metric Localisation using Appearance Transfer

We present a method of improving visual place recognition and metric loc...

Ghost-dil-NetVLAD: A Lightweight Neural Network for Visual Place Recognition

Visual place recognition (VPR) is a challenging task with the unbalance ...

Please sign up or login with your details

Forgot password? Click here to reset