# Filtering Empty Camera Trap Images in Embedded Systems

arXiv: https://arxiv.org/abs/2104.08859 · HTML: https://mlsanity.com/paper/2104.08859/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 27 references that are in the map.
- First posted on arXiv 18 Apr 2021.

## Builds on (most cited first, 15 of 15)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Big Transfer (BiT): General Visual Representation Learning](https://mlsanity.com/paper/1912.11370/) (2019)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Bag of Tricks for Image Classification with Convolutional Neural Networks](https://mlsanity.com/paper/1812.01187/) (2018)
- [Speed/accuracy trade-offs for modern convolutional object detectors](https://mlsanity.com/paper/1611.10012/) (2016)
- [MobileDets: Searching for Object Detection Architectures for Mobile Accelerators](https://mlsanity.com/paper/2004.14525/) (2020)
- [Towards Automatic Wild Animal Monitoring: Identification of Animal Species in Camera-trap Images using Very Deep Convolutional Neural Networks](https://mlsanity.com/paper/1603.06169/) (2016)

## Built on by (most cited first, 7 of 7)

- [Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding](https://mlsanity.com/paper/2204.08129/) (2022)
- [The PanAf-FGBG Dataset: Understanding the Impact of Backgrounds in Wildlife Behaviour Recognition](https://mlsanity.com/paper/2502.21201/) (2025)
- [OpenAnimalTracks: A Dataset for Animal Track Recognition](https://mlsanity.com/paper/2406.09647/) (2024)
- [Bag of Tricks for Long-Tail Visual Recognition of Animal Species in Camera-Trap Images](https://mlsanity.com/paper/2206.12458/) (2022)
- [Towards Scalable Insect Monitoring: Ultra-Lightweight CNNs as On-Device Triggers for Insect Camera Traps](https://mlsanity.com/paper/2411.14467/) (2024)
- [PARDINUS: Weakly supervised discarding of photo-trapping empty images based on autoencoders](https://mlsanity.com/paper/2312.14812/) (2023)
- [Improving Semantic Coverage in AI Test & Evaluation through Generative Augmentation](https://mlsanity.com/paper/2610.13697/) (2026)

## Abstract (arXiv)

Monitoring wildlife through camera traps produces a massive amount of images, whose a significant portion does not contain animals, being later discarded. Embedding deep learning models to identify animals and filter these images directly in those devices brings advantages such as savings in the storage and transmission of data, usually resource-constrained in this type of equipment. In this work, we present a comparative study on animal recognition models to analyze the trade-off between precision and inference latency on edge devices. To accomplish this objective, we investigate classifiers and object detectors of various input resolutions and optimize them using quantization and reducing the number of model filters. The confidence threshold of each model was adjusted to obtain 96% recall for the nonempty class, since instances from the empty class are expected to be discarded. The experiments show that, when using the same set of images for training, detectors achieve superior performance, eliminating at least 10% more empty images than classifiers with comparable latencies. Considering the high cost of generating labels for the detection problem, when there is a massive number of images labeled for classification (about one million instances, ten times more than those available for detection), classifiers are able to reach results comparable to detectors but with half latency.