Find research datasets worth reusing

opencc-by-4.0Apr 2023View details →

Person detection using UWB and Monocular camera (With LiDAR ground-truth) 0.7m/s

This dataset was record using the ROS2-foxy framework and can be utilized with: <pre><code>ros2 bag play square_test_with_gt_2 </code></pre> <table> <tbody> <tr> <td>Name of ROS2 topic</td> <td>Type of ROS2 topic</td> <td>Information</td> </tr> <tr> <td>/Detections</td> <td>vision_msgs/msg/Detection2DArray</td> <td>This topic includes person detections from the monocular camera that is performing the Deep Learning object detection</td> </tr> <tr> <td>/GT_POINT</td> <td>geometry_msgs/msg/PointStamped</td> <td>Contains the PointStamped message obtained from the LiDAR person detection for ground truth purposes</td> </tr> <tr> <td>/distance_data_array</td> <td>itrci_hardware/msg/RadioRangeDataArray</td> <td>This topic has person detections from the 3 UWB Anchors relative to the person TAG (Note that is in custom ros2 message itrci_hardware)</td> </tr> <tr> <td>/tf</td> <td>tf2_msgs/msg/TFMessage</td> <td>base_link and odom tf (robot is static)</td> </tr> <tr> <td>/tf_static</td> <td>tf2_msgs/msg/TFMessage</td> <td>Contains tf information of LiDAR cameras and anchors relative to the robot base_link</td> </tr> </tbody> </table>

opennotspecifiedApr 2017View details →

Figure 4 in Use of remote cameras to evaluate ocelot (Leopardus pardalis) population parameters in seasonal tropical dry forests of central-western Mexico

Figure 4: Relationship between estimated ocelot density and precipitation in tropical rain forests (TRF) and tropical seasonal ecosystems (TSE). Ocelot density in tropical rain forest was the closest to show a significant increase with annual precipitation (R2 = 0.2463, p = 0.071).

opennotspecifiedApr 2017View details →

Figure 3 in Use of remote cameras to evaluate ocelot (Leopardus pardalis) population parameters in seasonal tropical dry forests of central-western Mexico

Figure 3: Estimated ocelot density in tropical rainforest sites (TRF) and tropical seasonal ecosystems (TSE). Thick horizontal lines correspond to median values. The upper and lower extremes of the boxes correspond to the first and third quartiles, whiskers correspond to 1.5 times the interquartile range of the data and empty circles are outliers.

opennotspecifiedApr 2017View details →

Figure 2 in Use of remote cameras to evaluate ocelot (Leopardus pardalis) population parameters in seasonal tropical dry forests of central-western Mexico

Figure 2: Examples of markings employed for individual recognition of ocelots. (A) and (B) Photographic recapture of same individual in the locality of El Naranjal. (C) and (D) Different individuals recorded in the locality of Playa del Venado. The oval indicates an example of a set of unique spot and stripes patterns employed for individual identification.

Fig. 1 in Socio-spatial organization and kin structure in ocelots from integration of camera trapping and noninvasive genetics

Fig. 1.—Map of Barro Colorado Island, Panama, showing the locations of camera traps placed along trails and at ocelot (Leopardus pardalis) latrines.

Fig. 2 in Socio-spatial organization and kin structure in ocelots from integration of camera trapping and noninvasive genetics

Fig. 2.—Cumulative frequency distributions of association index values among pairs of male versus female ocelots (Leopardus pardalis) on Barro Colorado Island, Panama. Half-weight association index values represent the strength of spatiotemporal overlap between same-sex dyads based on how often they were photographed at the same camera trap within the same 30-day interval.

Fig. 4 in Socio-spatial organization and kin structure in ocelots from integration of camera trapping and noninvasive genetics

Fig. 4.—Relatedness of individual ocelots (Leopardus pardalis) on Barro Colorado Island, Panama, depending on sex and overlap of space use. Values shown are observed mean differences in relatedness between dyads of individual ocelots with overlapping space use (vertical bold lines) versus all dyads in the sampled population, along with the cumulative distribution of simulated differences from 1,000,000 randomly generated bootstrap replicates. Reference lines represent quantiles from the simulated distribution. A) All dyads, B) male-female dyads, C) male-male dyads, and D) female-female dyads.

Fig. 3 in Socio-spatial organization and kin structure in ocelots from integration of camera trapping and noninvasive genetics

Fig. 3.—Half-weight association index values between pairs of a) female and b) male ocelots (Leopardus pardalis) from Barro Colorado Island, Panama, shown in both matrix and graphical format. Values and line weights represent the strength (on a scale of 0–1) of spatiotemporal overlap between pairs of individuals based on how often they were photographed at the same camera trap during the same 30-day period. Asterisks represent associations and double asterisks represent dissociations that differed from random expectations (P <0.05).

opencc-by-nc-4.0Apr 2023View details →

High-speed camera recordings of unsteady flow in a multistage helico-axial pump

High-speed camera recordings of the unsteady flow in a multistage helico-axial pump. Covers a range of relative flow rates from 133 to 45% of the best efficiency point. A test rig with a transparent pump casing, comprising three low-specific speed compression stages was commissioned in a flow loop which allows a variety of pump inlet conditions with water and nitrogen as process fluids. A small amount of nitrogen was injected at the inlet and used as tracers in the flow. Recordings focus on the second stage of the pump.

opencc-by-4.0Apr 2023View details →

Fast Trajectory End-Point Prediction with Event Cameras for Reactive Robot Control

If you use any of this data, please cite the following publication: @inproceedings{monforte2023fast,   title={Fast Trajectory End-Point Prediction with Event Cameras for Reactive Robot Control},   author={Monforte, Marco and Gava, Luna and Iacono, Massimiliano and Glover, Arren and Bartolozzi, Chiara},   booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},   pages={4035--4043},   year={2023} } Event-based datasets of synthetic and real trajectories of a bouncing ball. The synthetic trajectories were obtained converting frames taken using Unreal Engine to events. The ground truth is provided along with objects and camera settings. The real trajectories wer dumped from a real event camera located in front of the robot workspace. To import .log files containing events, we suggest <a href="https://github.com/event-driven-robotics/bimvee">bimvee</a> Python library. Specifically use the functions to import .log files: data = importIitYarpBinaryDataLog(filePathOrName=input_path)

opennotspecifiedSep 2023View details →

Camera Dataset - Solomatov and Akkaynak (2023)

Source URL: <a href="https://color-lab-eilat.github.io/Spectral-sensitivity-estimation-web/#camera-dataset-section">https://color-lab-eilat.github.io/Spectral-sensitivity-estimation-web/#camera-dataset-section</a> Abstract A number of problems in computer vision and related fields would be mitigated if camera spectral sensitivities were known. As consumer cameras are not designed for high-precision visual tasks, manufacturers do not disclose spectral sensitivities. Their estimation requires a costly optical setup, which triggered researchers to come up with numerous indirect methods that aim to lower cost and complexity by using color targets. However, the use of color targets gives rise to new complications that make the estimation more difficult, and consequently, there currently exists no simple, low-cost, robust go-to method for spectral sensitivity estimation that non-specialized research labs can adopt. Furthermore, even if not limited by hardware or cost, researchers frequently work with imagery from multiple cameras that they do not have in their possession. To provide a practical solution to this problem, we propose a framework for spectral sensitivity estimation that not only does not require any hardware (including a color target), but also does not require physical access to the camera itself. Similar to other work, we formulate an optimization problem that minimizes a two-term objective function: a camera-specific term from a system of equations, and a universal term that bounds the solution space. Different than other work, we utilize publicly available high-quality calibration data to construct both terms. We use the colorimetric mapping matrices provided by the Adobe DNG Converter to formulate the camera-specific system of equations, and constrain the solutions using an autoencoder trained on a database of ground-truth curves. On average, we achieve reconstruction errors as low as those that can arise due to manufacturing imperfections between two copies of the same camera. We provide predicted sensitivities for more than 1,000 cameras that the Adobe DNG Converter currently supports, and discuss which tasks can become trivial when camera responses are available.

opencc-by-4.0Oct 2023View details →

Agouti camera trap data Paul Braun

Personal Agouti camera trap data collected by Paul Braun.

opencc-by-4.0Oct 2023View details →

High-resolution images from stationary cameras of the Puigcercós cliff in Spain.

This repository comprises high-resolution images captured by fixed cameras in Puigcercós, Spain. These images are utilized for quality assessment and the detection of rockfalls. Only one image is included for each camera and epoch. If more images are required, please contact the author.Folder Fig. 5 - Accuracy_analysis includes images from 4 still cameras from 3 and 5 July 2020.Folder Fig. 6 - Rockfall_analysis includes the images for the comparison of Figure 6 of the article. The images correspond to 21 March 2019, 23 January 2020 and 13 March 2020.Results and more information about the images can be found in the article:Blanch, X., Guinau, M., Eltner, A., and Abellan, A. 2023. Fixed photogrammetric systems for natural hazard monitoring with high spatio-temporal resolution, Nat. Hazards Earth Syst. Sci. Discuss, https://doi.org/10.5194/nhess-2023-79

Phenological time lapse images from landscape camera MC124 in Lammi Mixed stand

This record contains phenological time lapse images from camera Lammi Mixed stand. Camera was mounted at landscape view level at location 61.05356; 25.03898(N;E, WGS84). First set of images were taken between 23.11.2015--31.12.2016 (Version 1). Subsequent Versions extend the record with newer images, and the version number indicates the years covered by the record. Cameras were set to fix white balance, brightness automatically adjusted by camera.Image have equal resolution throughout the time series, time indicated in UTC+2. Images are taken half-hourly during fixed day-time period over the year. Gaps in time series and dark images possibly exist. More details on the camera installations and operation history can be found at 10.5281/zenodo.777952 The cameras were set up and images collected under EU Life+ (LIFE ENV/FI/000409) Monimet project, http://monimet.fmi.fi. For further information contact john.loehr@helsinki.fi

Phenological time lapse images from crown camera MC123 in Lammi Birch stand

This record contains phenological time lapse images from x camera Lammi Birch stand. Camera was mounted at crown view level at location 61.05211; 25.04180(N;E, WGS84). First set of images were taken between 08.05.2015--31.12.2016 (Version 1). Subsequent Versions extend the record with newer images, and the version number indicates the years covered by the record. Cameras were set to fix white balance, brightness automatically adjusted by camera.Image have equal resolution throughout the time series, time indicated in UTC+2. Images are taken half-hourly during fixed day-time period over the year. Gaps in time series and dark images possibly exist. More details on the camera installations and operation history can be found at 10.5281/zenodo.777952 The cameras were set up and images collected under EU Life+ (LIFE ENV/FI/000409) Monimet project, http://monimet.fmi.fi. For further information contact john.loehr@helsinki.fi

Phenological time lapse images from crown camera MC120 in Värriö Pine stand

This record contains phenological time lapse images from camera Värriö Pine stand. Camera was mounted at crown view level at location 67.75488;29.60989(N;E, WGS84). First set of images were taken between 13.04.2015--31.12.2016 (Version 1). Subsequent Versions extend the record with newer images, and the version number indicates the years covered by the record. Cameras were set to fix white balance, brightness automatically adjusted by camera.Image have equal resolution throughout the time series, time indicated in UTC+2. Images are taken half-hourly during fixed day-time period over the year. Gaps in time series and dark images possibly exist. More details on the camera installations and operation history can be found at doi 10.5281/zenodo.777952 The cameras were set up and images collected under EU Life+ (LIFE ENV/FI/000409) Monimet project, http://monimet.fmi.fi. For further information contact Pasi Kolari (pasi.kolari@helsinki.fi)

Phenological time lapse images from canopy camera MC119 in Värriö Pine stand

This record contains phenological time lapse images from camera Värriö Pine stand. Camera was mounted at canopy view level at location 67.75488;29.61000(N;E, WGS84). First set of images were taken between 13.04.2015--31.12.2016 (Version 1). Subsequent Versions extend the record with newer images, and the version number indicates the years covered by the record. Cameras were set to fix white balance, brightness automatically adjusted by camera.Image have equal resolution throughout the time series, time indicated in UTC+2. Images are taken half-hourly during fixed day-time period over the year. Gaps in time series and dark images possibly exist. More details on the camera installations and operation history can be found at doi 10.5281/zenodo.777952 The cameras were set up and images collected under EU Life+ (LIFE ENV/FI/000409) Monimet project, http://monimet.fmi.fi. For further information contact Pasi Kolari (pasi.kolari@helsinki.fi)

Phenological time lapse images from crown camera MC106 in Hyytiälä Pine stand

This record contains phenological time lapse images from camera Hyytiälä Pine stand. Camera was mounted at crown view level at location 61.84740;24.29529(N;E, WGS84). First set of images were taken between 13.03.2014--31.12.2016 (Version 1). Subsequent Versions extend the record with newer images, and the version number indicates the years covered by the record. Cameras were set to fix white balance, brightness automatically adjusted by camera.Image have equal resolution throughout the time series, time indicated in UTC+2. Images are taken half-hourly during fixed day-time period over the year. Gaps in time series and dark images possibly exist. More details on the camera installations and operation history can be found at doi 10.5281/zenodo.777952 The cameras were set up and images collected under EU Life+ (LIFE ENV/FI/000409) Monimet project, http://monimet.fmi.fi. For further information contact Pasi Kolari (pasi.kolari@helsinki.fi)

Phenological time lapse images from crown camera MC109 in Sodankylä Pine stand

This record contains phenological time lapse images from camera Sodankylä Pine stand. Camera was mounted at crown view level at location 67.3618;26.638167(N;E, WGS84). First set of images were taken between 22.05.2014--31.12.2016 (Version 1). Subsequent Versions extend the record with newer images, and the version number indicates the years covered by the record. Cameras were set to fix white balance, brightness automatically adjusted by camera.Image have equal resolution throughout the time series, time indicated in UTC+2. Images are taken half-hourly during fixed day-time period over the year. Gaps in time series and dark images possibly exist. More details on the camera installations and operation history can be found at doi 10.5281/zenodo.777952 The cameras were set up and images collected under EU Life+ (LIFE ENV/FI/000409) Monimet project, http://monimet.fmi.fi. For further information contact mika.aurela@fmi.fi

Phenological time lapse images from landscape camera MC125 in Lammi Mixed stand

This record contains phenological time lapse images from camera Lammi Mixed stand. Camera was mounted at landscape view level at location 61.05356; 25.03898(N;E, WGS84). First set of images were taken between 23.11.2015--31.12.2016 (Version 1). Subsequent Versions extend the record with newer images, and the version number indicates the years covered by the record. Cameras were set to fix white balance, brightness automatically adjusted by camera.Image have equal resolution throughout the time series, time indicated in UTC+2. Images are taken half-hourly during fixed day-time period over the year. Gaps in time series and dark images possibly exist. More details on the camera installations and operation history can be found at doi 10.5281/zenodo.777952 The cameras were set up and images collected under EU Life+ (LIFE ENV/FI/000409) Monimet project, http://monimet.fmi.fi. For further information contact john.loehr@helsinki.fi