The Mammal Collection of UENF was created in 2013 to document the biodiversity of northern Rio de Janeiro, and house voucher specimens collected during field research held by professors from the university and collaborating institutions. The collection currently holds 440 physical vouchers, mostly bats, and includes noteworthy records, such as the first Promops nasutus reported for the state of Rio de Janeiro. To these physical vouchers, we recently added a digital bioacoustics collection (343 files of bat distress calls) and a camera-trap multimedia collection (2683 videos or photographs of small to large-sized mammals). In this paper, we provide an overview of these holdings, and highlight and discuss the importance of regional scientific collections, along with the fundamental role of publishing their records in online databases in order to increase their visibility and scientific use. Finally, we discuss the importance of natural history collections to society, emphasizing that improving the awareness of the general public on the role of these collections to scientific development will be crucial for their conservation over the next centuries.
Camera traps deployed in remote locations provide an effective method for ecologists to monitor and study wildlife in a non-invasive way. However, current camera traps suffer from two problems. First, the images are manually classified and counted, which is expensive. Second, due to manual coding, the results are often stale by the time they get to the ecologists. Using the Internet of Things (IoT) combined with deep learning represents a good solution for both these problems, as the images can be classified automatically, and the results immediately made available to ecologists. This paper proposes an IoT architecture that uses deep learning on edge devices to convey animal classification results to a mobile app using the LoRaWAN low-power, wide-area network. The primary goal of the proposed approach is to reduce the cost of the wildlife monitoring process for ecologists, and to provide real-time animal sightings data from the camera traps in the field. Camera trap image data consisting of 66,400 images were used to train the InceptionV3, MobileNetV2, ResNet18, EfficientNetB1, DenseNet121, and Xception neural network models. While performance of the trained models was statistically different (Kruskal–Wallis: Accuracy H(5) = 22.34, p < 0.05; F1-score H(5) = 13.82, p = 0.0168), there was only a 3% difference in the F1-score between the worst (MobileNet V2) and the best model (Xception). Moreover, the models made similar errors (Adjusted Rand Index (ARI) > 0.88 and Adjusted Mutual Information (AMU) > 0.82). Subsequently, the best model, Xception (Accuracy = 96.1%; F1-score = 0.87; F1-Score = 0.97 with oversampling), was optimized and deployed on the Raspberry Pi, Google Coral, and Nvidia Jetson edge devices using both TenorFlow Lite and TensorRT frameworks. Optimizing the models to run on edge devices reduced the average macro F1-Score to 0.7, and adversely affected the minority classes, reducing their F1-score to as low as 0.18. Upon stress testing, by processing 1000 images consecutively, Jetson Nano, running a TensorRT model, outperformed others with a latency of 0.276 s/image (s.d. = 0.002) while consuming an average current of 1665.21 mA. Raspberry Pi consumed the least average current (838.99 mA) with a ten times worse latency of 2.83 s/image (s.d. = 0.036). Nano was the only reasonable option as an edge device because it could capture most animals whose maximum speeds were below 80 km/h, including goats, lions, ostriches, etc. While the proposed architecture is viable, unbalanced data remain a challenge and the results can potentially be improved by using object detection to reduce imbalances and by exploring semi-supervised learning.
Kon Ka Kinh National Park (KKK NP) is a priority zone for biodiversity protection in Vietnam as well as ASEAN. In order to survey the current fauna species diversity in the southern part of the KKK NP, we conducted camera trapping surveys in 2017, 2018, and 2019. 28 infrared camera traps were set up on elevations between 1041 to 1497 meters. In total, there were 360 days of survey using camera trap. As result, we recorded a total of 27 animal species of those, five species are listed in the IUCN Red List of Threatened Species (IUCN, 2020). The survey results showed a high richness of wildlife in the southern park region, and it also revealed human disturbance to wildlife in the park. The first-time camera trap was used for surveying wildlife diversity in the southern region of the KKK NP. Conducting camera trap surveys in the whole KKK NP is essential for monitoring and identifying priority areas for wildlife conservation in the national park.
A long-term camera-trap study of the Javan Rhinoceros in 2013 in Ujung Kulon National Park (UKNP), Indonesia, allowed us to document the first photographic evidence of Dholes preying on a young Banteng and other species. Our photographs suggested that Dholes get in large packs to predate on Banteng and commonly separate young from adults when attacking the young. Future research should examine the Dhole diet and interspecific relationships between Dhole and Banteng to gain a better understanding of the ecological impacts of endangered predators on endangered prey in UKNP.
Latrine sites are the places used for urination and defecation, which mostly act as a signaling agent for multiple purposes like territorial marking, confrontation with extruders or potential predators, delivering different inter and intra-communication messages. To understand latrine site visit pattern, a single camera trap was deployed for 91 trap nights at the latrine site of Large Indian Civet during the months of December 2016 and February & March 2017. Latrine site was found under the tree with abundant crown cover and bushes. At least two individuals were found to be using a single latrine site in an irregular manner between 1800 h and 0600 h with higher activity between 1800 h and 2300 h. Our results indicated an irregular latrine site visit pattern, hence similar studies with a robust research design in larger areas are required to understand specific latrine use patterns.
The fishing cat’s persistence in a ‘semi-aquatic niche’ suggests the evolution of a successful hunting strategy. We describe it for the first time by analysing 197 camera-trap video-clips, collected from a participatory-science initiative, within an ethogram framework. The cats spent ∼52% of the time sitting and waiting for prey (fishes) to come nearer and took limited attempts to hunt (3.89%) in deeper waters (in which the upper portions of the cat’s body were submerged), where its hunting success was found to be 42.86%. In shallow waters, it adopted a predominantly active mode of hunting (∼96%) to flush out prey.