# Intersection Prediction from Single 360deg Image via Deep Detection of Possible Direction of Travel

arXiv: https://arxiv.org/abs/2204.04634 · HTML: https://mlsanity.com/paper/2204.04634/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 19 references that are in the map.
- First posted on arXiv 10 Apr 2022.

## Builds on (most cited first, 7 of 7)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image](https://mlsanity.com/paper/1803.08999/) (2018)
- [Orientation-aware Semantic Segmentation on Icosahedron Spheres](https://mlsanity.com/paper/1907.12849/) (2019)
- [Building Movie Map -- A Tool for Exploring Areas in a City -- and its Evaluation](https://mlsanity.com/paper/2011.08525/) (2020)

## Built on by (most cited first, 1 of 1)

- [InterLoc: LiDAR-based Intersection Localization using Road Segmentation with Automated Evaluation Method](https://mlsanity.com/paper/2505.00512/) (2025)

## Abstract (arXiv)

Movie-Map, an interactive first-person-view map that engages the user in a simulated walking experience, comprises short 360deg video segments separated by traffic intersections that are seamlessly connected according to the viewer's direction of travel. However, in wide urban-scale areas with numerous intersecting roads, manual intersection segmentation requires significant human effort. Therefore, automatic identification of intersections from 360deg videos is an important problem for scaling up Movie-Map. In this paper, we propose a novel method that identifies an intersection from individual frames in 360deg videos. Instead of formulating the intersection identification as a standard binary classification task with a 360deg image as input, we identify an intersection based on the number of the possible directions of travel (PDoT) in perspective images projected in eight directions from a single 360deg image detected by the neural network for handling various types of intersections. We constructed a large-scale 360deg Image Intersection Identification (iii360) dataset for training and evaluation where 360deg videos were collected from various areas such as school campus, downtown, suburb, and china town and demonstrate that our PDoT-based method achieves 88% accuracy, which is significantly better than that achieved by the direct naive binary classification based method. The source codes and a partial dataset will be shared in the community after the paper is published.