# FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras

arXiv: https://arxiv.org/abs/1707.09476 · HTML: https://mlsanity.com/paper/1707.09476/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2017.

## Built on by (most cited first, 27 of 27)

- [CLIP-Count: Towards Text-Guided Zero-Shot Object Counting](https://mlsanity.com/paper/2305.07304/) (2023)
- [TransCrowd: weakly-supervised crowd counting with transformers](https://mlsanity.com/paper/2104.09116/) (2021)
- [STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning](https://mlsanity.com/paper/2308.10468/) (2023)
- [Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark](https://mlsanity.com/paper/2105.02440/) (2021)
- [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021)
- [The Caltech Fish Counting Dataset: A Benchmark for Multiple-Object Tracking and Counting](https://mlsanity.com/paper/2207.09295/) (2022)
- [T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting](https://mlsanity.com/paper/2502.20625/) (2025)
- [Scene-Adaptive Attention Network for Crowd Counting](https://mlsanity.com/paper/2112.15509/) (2021)
- [Spatio-channel Attention Blocks for Cross-modal Crowd Counting](https://mlsanity.com/paper/2210.10392/) (2022)
- [Mind the Prompt: A Novel Benchmark for Prompt-based Class-Agnostic Counting](https://mlsanity.com/paper/2409.15953/) (2024)
- [Backdoor Attacks on Crowd Counting](https://mlsanity.com/paper/2207.05641/) (2022)
- [CrowdMLP: Weakly-Supervised Crowd Counting via Multi-Granularity MLP](https://mlsanity.com/paper/2203.08219/) (2022)
- [A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approaches](https://mlsanity.com/paper/2501.19184/) (2025)
- [CountingDINO: A Training-free Pipeline for Class-Agnostic Counting using Unsupervised Backbones](https://mlsanity.com/paper/2504.16570/) (2025)
- [Vision Technologies with Applications in Traffic Surveillance Systems: A Holistic Survey](https://mlsanity.com/paper/2412.00348/) (2024)
- [Cross-Region Building Counting in Satellite Imagery using Counting Consistency](https://mlsanity.com/paper/2110.13558/) (2021)
- [Turning Traffic Monitoring Cameras into Intelligent Sensors for Traffic Density Estimation](https://mlsanity.com/paper/2111.00941/) (2021)
- [Domain Randomization for Object Counting](https://mlsanity.com/paper/2202.08670/) (2022)
- [Tensor Factorization for Leveraging Cross-Modal Knowledge in Data-Constrained Infrared Object Detection](https://mlsanity.com/paper/2309.16592/) (2023)
- [MarsSeg: Mars Surface Semantic Segmentation with Multi-level Extractor and Connector](https://mlsanity.com/paper/2404.04155/) (2024)
- [Does it Really Count? Assessing Semantic Grounding in Text-Guided Class-Agnostic Counting](https://mlsanity.com/paper/2605.02752/) (2026)
- [Deep Learning Techniques for Visual Counting](https://mlsanity.com/paper/2206.03033/) (2022)
- [Multi-task Learning for Sparse Traffic Forecasting](https://mlsanity.com/paper/2211.09984/) (2022)
- [Deep Learning Enhanced Road Traffic Analysis: Scalable Vehicle Detection and Velocity Estimation Using PlanetScope Imagery](https://mlsanity.com/paper/2410.14698/) (2024)
- [A Unified Object Counting Network with Object Occupation Prior](https://mlsanity.com/paper/2212.14193/) (2022)
- [ANTHROPOS-V: benchmarking the novel task of Crowd Volume Estimation](https://mlsanity.com/paper/2501.01877/) (2025)
- [Scaling Traffic Insights with AI and Language Model-Powered Camera Systems for Data-Driven Transportation Decision Making](https://mlsanity.com/paper/2510.09981/) (2025)

## Abstract (arXiv)

In this paper, we develop deep spatio-temporal neural networks to sequentially count vehicles from low quality videos captured by city cameras (citycams). Citycam videos have low resolution, low frame rate, high occlusion and large perspective, making most existing methods lose their efficacy. To overcome limitations of existing methods and incorporate the temporal information of traffic video, we design a novel FCN-rLSTM network to jointly estimate vehicle density and vehicle count by connecting fully convolutional neural networks (FCN) with long short term memory networks (LSTM) in a residual learning fashion. Such design leverages the strengths of FCN for pixel-level prediction and the strengths of LSTM for learning complex temporal dynamics. The residual learning connection reformulates the vehicle count regression as learning residual functions with reference to the sum of densities in each frame, which significantly accelerates the training of networks. To preserve feature map resolution, we propose a Hyper-Atrous combination to integrate atrous convolution in FCN and combine feature maps of different convolution layers. FCN-rLSTM enables refined feature representation and a novel end-to-end trainable mapping from pixels to vehicle count. We extensively evaluated the proposed method on different counting tasks with three datasets, with experimental results demonstrating their effectiveness and robustness. In particular, FCN-rLSTM reduces the mean absolute error (MAE) from 5.31 to 4.21 on TRANCOS, and reduces the MAE from 2.74 to 1.53 on WebCamT. Training process is accelerated by 5 times on average.