Exploiting Depth Information for Wildlife Monitoring

By Timm Haucke, Volker Steinhage. 2021

16 citations recorded by the source corpus.

Camera traps are a proven tool in biology and specifically biodiversity research. However, camera traps including depth estimation are not widely deployed, despite providing valuable context about the scene and facilitating the automation of previously laborious manual ecological methods. In this study, we propose an automated camera trap-based approach to detect and identify animals using depth estimation. To detect and identify individual animals, we propose a novel method D-Mask R-CNN for the so-called instance segmentation which is a deep learning-based technique to detect and delineate each distinct object of interest appearing in an image or a video clip. An experimental evaluation shows the benefit of the additional depth estimation in terms of improved average precision scores of the animal detection compared to the standard approach that relies just on the image information. This novel approach was also evaluated in terms of a proof-of-concept in a zoo scenario using an RGB-D camera trap.

Subfields: Computer Vision and Pattern Recognition, Environmental Engineering, 3D Vision & Pose

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Christoph Feichtenhofer
2. Luc Van Gool
3. Cordelia Schmid
4. Junting Pan
5. Jitendra Malik
6. Xiaogang Wang
7. Dacheng Tao
8. Trevor Darrell

In Environmental Engineering

1. Hjalmar S. Kühl
2. Peter Johanns
3. Timm Haucke
4. Volker Steinhage
5. Piotr Doll'ar

In 3D Vision & Pose

1. Hjalmar S. Kühl
2. Peter Johanns
3. Timm Haucke
4. Volker Steinhage
5. Christoph Feichtenhofer
6. Piotr Doll'ar

Citations in the corpus

• SOCRATES: Introducing Depth in Visual Wildlife Monitoring Using Stereo Vision (2022, methodology): “Reference [11] instead used an Intel RealSense D435 stereo camera, which computes stereo correspondence on the camera itself.”
• SAM 2: Segment Anything in Images and Videos (2024, methodology): “The video datasets used are listed as follows: Lindenthal Camera Traps (LCT) (Haucke & Steinhage, 2021), VOST (Tokmakov et al., 2022), LV-VIS (Wang et al., 2023), FBMS (Brox et al., 2010), Virtual KITTI 2 (Cabon et al., 2020), Corsican Fire Database (CFD) (Toulouse et al., 2017), VIPSeg (Miao et…”
• Automated distance estimation for wildlife camera trapping (2022, methodology): “• Lindenthal is, to our best knowledge, the only outdoor dataset that provides depth as well as tracking information of observed animals (Haucke and Steinhage, 2021).”
• Overcoming the distance estimation bottleneck in estimating animal abundance with camera traps (2021, unknown): “…only once when the camera traps are installed (Howe et al., 2017) or be placed permanently in the scene (Palencia Camera traps including depth estimation are currently just subject to research on wildlife monitoring (Haucke and Steinhage, 2021). et al., 2021) to be visible in each observation.”