Presented by: Nicholas Sandor

Date: Tuesday, April 14, 2026
Time: 1:00 pm - 2:00 pm
Place: Elliott 226

Abstract: 

Halide perovskites are a highly promising class of emerging semiconductor materials with applications in solar energy and medical imaging. Single crystals of this material are an ideal form with high performance, and controlling single crystal growth is critical for creating reproducible high-quality devices; however, monitoring these processes is hindered by a lack of tools capable of persistently tracking growth proceses. To address this, we present CrystalCV: an accessible, Python-based computer vision platform designed to continuously extract time-series crystallization data for multiple crystals. The system's utility is demonstrated across three case studies: measuring MAPbBr3 and CsPbBr3 growth uniformity, validating reactive thermal control to suppress secondary nucleation, and monitoring FAPbI3 phase transitions. CrystalCV offers a highly accessible solution to accelerate the optimization of complex semiconductor crystal growth.

Presented by: Abida Sultana

Date: Wednesday, April 15, 2026
Time: 9:00 am
Place: Zoom - see below.

Join Zoom Meeting
https://uvic.zoom.us/j/4534002368?pwd=2Yu38RsexfniB1auf3UBNsVqw8ByMH.1&omn=87889111010

Meeting ID: 453 400 2368
Password: 658037
One tap mobile
+16475580588,,4534002368# Canada
+17789072071,,4534002368# Canada

Dial by your location
+1 647 558 0588 Canada
+1 778 907 2071 Canada
Meeting ID: 453 400 2368
Find your local number: https://uvic.zoom.us/u/kbY9u23Uyd

Abstract: Estimating metric object distance from a single RGB image is challenging because monocular depth does not provide an absolute scale. Existing solutions either require active sensors such as LiDAR or stereo, rely on monocular depth that remains scale-ambiguous, or use implicit vision-language reasoning that can be unstable for precise measurement. This thesis proposes a semantic–geometric pipeline for recovering metric scale by combining open-vocabulary object grounding and segmentation, label normalization, monocular depth, and camera cues. Object-centric 3D points are reconstructed from the predicted depth, an oriented 3D bounding box is fitted to estimate object dimensions, and real-world size priors are used to compute a scale factor that converts relative depth into absolute distance. The proposed method is evaluated on HOT3D, ScanNet, ARKitScenes, and a custom iPhone dataset, achieving Multi-Threshold Relative Accuracy (MRA) values of 68.85%, 88.30%, 75.12%, and 89.85%, respectively, under the per-frame average mean-distance strategy. The results show that frame-level averaging improves stability by reducing the influence of instance-level outliers. The main limitations of the approach are its dependence on segmentation and depth quality, sensitivity to canonical size priors for categories with high size variation, possible instability under occlusion or truncation, and relatively high processing time. Future work includes more robust scale estimation, adaptive size priors, improved object fitting, the use of consecutive frames for temporal consistency, and pipeline optimization for lower latency.