Hi all,

My name is Peter van Lunteren and I’m a wildlife ecologist from The Netherlands. I’m not really an entomologist nor do I work much with insects - I’m just an enthusiast ;) Tom’s video on The WILDLABS Variety Hour has motivated me to join this discussion group.

I have made an open source application called EcoAssist where people can train and deploy YOLOv5 object detection models. It started out as a GUI for the MegaDetector model to filter out empty camera trap images, but evolved to become a platform where ecologists can transfer knowledge from existing models to easily train their own species classifiers.

I was wondering whether it would be possible to include an insect detection model to the application, so that people can use it as a starting point to train their own insect model. Unfortunately, though, it is limited to YOLOv5 models. Does anyone know of a YOLOv5 insect detection model?

Cheers and keep up the good work,

Peter

Hi Andrew,

If I understand you correctly, you want to turn on the LEDs when USB power is applied.  The easiest way I can see to do this is to reroute the red wire to USBC VBUS, via an appropriate current limiting resistor.  This bypasses all the electronics in your photo.

You could insert the current limiting resistor in the USB cable for better heat dissipation, or use a DC-DC constant current source instead of a resistor if power consumption is a concern.

Further to @htarold 's excellent suggestion, you can replace that entire PCB with a simple USB breakout board (e.g. USB micro attached below) by removing the red wire and attaching it to VCC on the breakout board, and removing and attaching the black wire to GND. 

Hi all! I'm part of a Pollinator Monitoring Program at California State University, San Marcos which was started by a colleague lecturer of mine who was interested in learning more about the efficacy of pollinator gardens. It grew to include comparing local natural habitat of the Coastal Sage Scrub and I was initially brought on board to assist with data analysis, data management, etc. We then pivoted to the idea of using camera traps and AI for insect detection in place of the in-person monitoring approach (for increasing data and adding a cool tech angle to the effort, given it is of interest to local community partners that have pollinator gardens). 

The group heavily involves students as researchers, and they are instrumental to the projects. We have settled on a combination of video footage and development of deep neural networks using the cloud-hosted video track detection tool, VIAME (developed by Kitware for NOAA Fisheries originally for fish track detection). Students built our first two PICTs (low-cost camera traps), and annotated the data from our pilot study that we are currently starting the process of network development for. Here's a cool pic of the easy-to-use interface that students use when annotating data: 

                                                    Figure 1: VIAME software demonstrating annotation of the track of an insect in the video (red box). Annotations are                                                           done manually to develop a neural network for the automated processing.

The goal of the group's camera trap team is develop a neural network that can track insect pollinators associated with a wide variety of plants, and to use this information to collect large datasets to better understand the pollinator occurrence and activities with local habitats. This ultimately relates to native habitat health and can be used for long-term tracking of changes in the ecosystem, with the idea that knowledge of pollinators may inform resources and conservation managers, as well as local organizations in their land use practices. We ultimately are interested in working with the Kitware folks further to not only develop a robust network (and share broadly of course!), but also to customize the data extraction from automated tracks to include automated species/species group identification and information on interaction rate by those pollinators. We would love any suggestions for appropriate proposals to apply to, as well as any information/suggestions regarding the PICT camera or suggestions on methods. We are looking to include night time data collection at some point as well and are aware the near infrared is advised, but would appreciate any thoughts/advice on that avenue as well. 

We will of course post when we have more results and look forward to hearing more about all the interesting projects happening in this space!

Cheers, 
Liz Ferguson 

@ShwetaMukundan I just saw this thesis published on tracking bees. Maybe you could use the same method? 

Hi @ShwetaMukundan,

this could be interesting for you:

https://www.science.org/doi/10.1126/scirobotics.abb0839

https://www.youtube.com/watch?v=VwiHf2T9bLU

https://edition.cnn.com/2020/10/13/us/murder-hornet-track-washington-trnd/index.html

All from this working group: 

https://homes.cs.washington.edu/~gshyam/

Hi Tom,

I'm with Akiba, you have to test.  A collaborator has deployed solar-augmented kit in secondary jungle and some of them got enough light, and others didn't, so it can work.  The open circuit voltage of solar panels doesn't change a whole lot in dim light, but the current drops drastically.  So you would choose an oversize panel of the same voltage (or a bit higher).

Thanks

I've been intrigued by this topic. Thinking about ways you could use drones or some kind of launcher to deploy panels above the canopy. Sadly I live in the great white north so I have no way of testing any concepts. Maybe even some kind of solar balloon that could float above the canopy. Interesting design problem.

Hey Tom,
Since the output is dependent on a couple of factors such as the solar irradiance of the place, shading from the canopy, the type of solar panels (mono, poly or amorphous) and orientation of the panels, etc, I'd suggest you use a software to simulate the different parameters to get an almost accurate estimation of the output. You can try PVsyst- it has a free month trial (I haven't used it before but I hear it's great) or any other PV software :)

Hello,

I'm working on a light weight light trap based on Bjerge et al 2021, however I opted to use an ArduCam 64mp (9152 x 6944 resolution). Designed for the pi specifically and at $60 it checks many of your criteria. I haven't put everything together yet so I can't speak for white balance and power usage, but the autofocus appears to work well from initial tests, and it is tiny.

Cheers,

Hubert