SPVSoAP3D: A Second-order Average Pooling Approach to enhance 3D Place Recognition in Horticultural Environments
3D LiDAR-based place recognition has been extensively researched in urban environments, yet it remains underexplored in agricultural settings. Unlike urban contexts, horticultural environments, characterized by their permeability to laser beams, result in sparse and overlapping LiDAR scans with suboptimal geometries. This phenomenon leads to intra- and inter-row descriptor ambiguity. In this work, we address this challenge by introducing SPVSoAP3D, a novel modeling approach that combines a voxel-based feature extraction network with an aggregation technique based on a second-order average pooling operator, complemented by a descriptor enhancement stage. Furthermore, we augment the existing HORTO-3DLM dataset by introducing two new sequences derived from horticultural environments. We evaluate the performance of SPVSoAP3D against state-of-the-art (SOTA) models, including OverlapTransformer, PointNetVLAD, and LOGG3D-Net, utilizing a cross-validation protocol on both the newly introduced sequences and the existing HORTO-3DLM dataset. The findings indicate that the average operator is more suitable for horticultural environments compared to the max operator and other first-order pooling techniques. Additionally, the results highlight the improvements brought by the descriptor enhancement stage.
Code (1)
Tasks
3D Place RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Second-Order Pooling for Graph Neural Networks
Graph neural networks have achieved great success in learning node representations for graph tasks such as node classification and link prediction. Graph representation learning requires graph pooling to obtain graph rep…
Graph ClassificationGraph Representation LearningLink PredictionNode Classification+1Building Sequential Inference Models for End-to-End Response Selection
This paper presents an end-to-end response selection model for Track 1 of the 7th Dialogue System Technology Challenges (DSTC7). This task focuses on selecting the correct next utterance from a set of candidates given a …
Conversational Response SelectionDescriptiveWord EmbeddingsWhy Mean Pooling Works: Quantifying Second-Order Collapse in Text Embeddings
For constructing text embeddings, mean pooling, which averages token embeddings, is the standard approach. This paper examines whether mean pooling actually works well in real models. First, we note that mean pooling can…
Speaker embeddings by modeling channel-wise correlations
Speaker embeddings extracted with deep 2D convolutional neural networks are typically modeled as projections of first and second order statistics of channel-frequency pairs onto a linear layer, using either average or at…
Speaker RecognitionStyle TransferSecond-order Temporal Pooling for Action Recognition
Deep learning models for video-based action recognition usually generate features for short clips (consisting of a few frames); such clip-level features are aggregated to video-level representations by computing statisti…
Action RecognitionTemporal Action Localization