# Enhanced Parking Perception by Multi-Task Fisheye Cross-view Transformers

arXiv: https://arxiv.org/abs/2408.12575 · HTML: https://mlsanity.com/paper/2408.12575/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 18 references that are in the map.
- First posted on arXiv 22 Aug 2024.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [Cross-view Transformers for real-time Map-view Semantic Segmentation](https://mlsanity.com/paper/2205.02833/) (2022)
- [M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation](https://mlsanity.com/paper/2204.05088/) (2022)
- [Vision-Centric BEV Perception: A Survey](https://mlsanity.com/paper/2208.02797/) (2022)
- [LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic Segmentation](https://mlsanity.com/paper/2206.13294/) (2022)
- [F2BEV: Bird's Eye View Generation from Surround-View Fisheye Camera Images for Automated Driving](https://mlsanity.com/paper/2303.03651/) (2023)
- [Attentional Graph Neural Network for Parking-slot Detection](https://mlsanity.com/paper/2104.02576/) (2021)
- [NVAutoNet: Fast and Accurate 360circ 3D Visual Perception For Self Driving](https://mlsanity.com/paper/2303.12976/) (2023)
- [Holistic Parking Slot Detection with Polygon-Shaped Representations](https://mlsanity.com/paper/2310.11629/) (2023)

## Built on by (most cited first, 4 of 4)

- [FisheyeGaussianLift: BEV Feature Lifting for Surround-View Fisheye Camera Perception](https://mlsanity.com/paper/2511.17210/) (2025)
- [Click-Calib: A Robust Extrinsic Calibration Method for Surround-View Systems](https://mlsanity.com/paper/2501.01557/) (2025)
- [Advancing Real-World Parking Slot Detection with Large-Scale Dataset and Semi-Supervised Baseline](https://mlsanity.com/paper/2509.13133/) (2025)
- [Valeo Near-Field: a novel dataset for pedestrian intent detection](https://mlsanity.com/paper/2510.15673/) (2025)

## Abstract (arXiv)

Current parking area perception algorithms primarily focus on detecting vacant slots within a limited range, relying on error-prone homographic projection for both labeling and inference. However, recent advancements in Advanced Driver Assistance System (ADAS) require interaction with end-users through comprehensive and intelligent Human-Machine Interfaces (HMIs). These interfaces should present a complete perception of the parking area going from distinguishing vacant slots' entry lines to the orientation of other parked vehicles. This paper introduces Multi-Task Fisheye Cross View Transformers (MT F-CVT), which leverages features from a four-camera fisheye Surround-view Camera System (SVCS) with multihead attentions to create a detailed Bird-Eye View (BEV) grid feature map. Features are processed by both a segmentation decoder and a Polygon-Yolo based object detection decoder for parking slots and vehicles. Trained on data labeled using LiDAR, MT F-CVT positions objects within a 25m x 25m real open-road scenes with an average error of only 20 cm. Our larger model achieves an F-1 score of 0.89. Moreover the smaller model operates at 16 fps on an Nvidia Jetson Orin embedded board, with similar detection results to the larger one. MT F-CVT demonstrates robust generalization capability across different vehicles and camera rig configurations. A demo video from an unseen vehicle and camera rig is available at: https://streamable.com/jjw54x.