Changes in the ungulate population density in the wild has impacts on both the wildlife and human society. In order to control the ungulate population movement, monitoring systems such as camera trap networks have been implemented in a non-invasive setup. However, such systems produce a large number of images as the output, hence making it very resource consuming to manually detect the animals. In this paper, we present a new dataset of wild ungulates which was collected in Latvia. Moreover, we demonstrate two methods, which use RetinaNet and Faster R-CNN as backbones, respectively, to detect the animals in the images. We discuss the optimization of training and impact of data augmentation on the performance. Finally, we show the result of aforementioned tune networks over the real world data collected in Latvia.

Passive acoustic sensors have the potential to become a valuable complementary component in red deer Cervus elaphus monitoring providing deeper insight into the behavior of stags during the rutting period. Automation of data acquisition and processing is crucial for adaptation and wider uptake of acoustic monitoring. Therefore, an automated data processing workflow concept for red deer call detection and localization was proposed and demonstrated. The unique dataset of red deer calls during the rut in September 2021 was collected with four GPS time-synchronized microphones. Five supervised machine learning algorithms were tested and compared for the detection of red deer rutting calls where the support-vector-machine-based approach demonstrated the best performance of −96.46% detection accuracy. For sound source location, a hyperbolic localization approach was applied. A novel approach based on cross-correlation and spectral feature similarity was proposed for sound delay assessment in multiple microphones resulting in the median localization error of 16 m, thus providing a solution for automated sound source localization—the main challenge in the automation of the data processing workflow. The automated approach outperformed manual sound delay assessment by a human expert where the median localization error was 43 m. Artificial sound records with a known location in the pilot territory were used for localization performance testing.

The overall increase of ungulate populations in modern Europe has contributed to conflicts in national economies, particularly between game management and the forestry sector. This study assessed damage risks to young pine (Pinus sylvestris L.), spruce (Picea abies (L.) H. Karst.) and aspen (Populus tremula L.) stands at two spatial scales. One level assessed the interaction between sex-age structure of cervid populations, measured by pellet group density, and forest damages, measured as the percentage of heavily browsed trees in 2040 stand surveys distributed proportionally throughout the country. The second level compared pellet counts and trail-camera-based records of moose (Alces alces L.) and red deer (Cervus elaphus L.) presence in a pilot study area. We examined whether 1) there is a correlation between damage amount and ungulate population structure and 2) are the data from trail cameras suitable for wider use in monitoring ungulate population structure. The study confirmed significantly higher moose pellet group densities in pine than in spruce and aspen stands. Pine damages were greater in stands with higher moose pellet group density, especially with female moose prevailing over male moose density index. The red deer pellet group densities were significantly higher in heavily damaged pine and spruce stands, regardless of sex-age structure. In most cases, there were no statistically significant differences between the two survey methods of ungulate population structure by using pellet count transects and trail camera fixations. Both methods provide comparable data on sex-age structure in moose and red deer populations if seasonal and habitat-predicted biases are considered. However, trail cameras are more widely applicable and easier to use by hunters than pellet counts.