KRISTINA TICA. HUMAN OVERS[A]IGHT: THE OPS ROOM. 2025.COMPUTER VISION TEST OUTPUTS [OPTICAL FLOW]. CODE AND IMAGE BY KRISTINA TICA
_COMPUTER VISION
The computer vision model is trained on the selection of high-risk or life-threatening operations in real life, detecting armed policemen, demonstrations, military vehicles, and weapons, and attacked areas, demolitions, and environmental catastrophes such as wildfires. The model has been iteratively improved and fine-tuned, and the training objects and the arrays of labels are expected to grow throughout a longer research period.
Currently, there are three applications performing based on (1) object detection algorithms that include object masking, blurring out suspected subjects from the custom-trained model and overlaying the detected area with heatmaps [saliency maps]; and (2) video inpainting that fills in areas of objects detected in the video.
KRISTINA TICA. HUMAN OVERS[A]IGHT: THE OPS ROOM. 2025.COMPUTER VISION TEST OUTPUTS [SALIENCY MAP]. CODE BY LUKAS BIBL, IMAGE BY KRISTINA TICA
KRISTINA TICA. HUMAN OVERS[A]IGHT: THE OPS ROOM. 2025.COMPUTER VISION TEST OUTPUTS [SALIENCY MAP]. CODE BY LUKAS BIBL, IMAGE BY KRISTINA TICA
The references for the concept and the aesthetics of video installation come from the analysis of the operational image (Paglen, Parikka) as well as the concept of invisuality (MacKenzie and Munster), and the artwork series Eye Machine by Harun Farocki, and previous computer vision-based works of Tica (Digital Prayer, FUTUREFALSEPOSITIVE), problematising the notion machinic vision against the human eye, the computational pattern discrimination (Steyerl et. al) by statistical correlation against human’s contexts of representation, and of the causality of relations.
Left: IDF footage of Gazans looting aid trucks before deadly stampede [https://www.youtube.com/watch?v=PdTt7efaR2U]
Right: Harun FarockI. Eye Machine II. Courtesy of the artist and Harun Farocki Foundation.
The plan for the software development of the installation is to have each activity logged, in the capacity of [irreversibly] changing the system and its content. In such an iterative feedback loop, we explore how quickly human input can affect a seemingly organised system and change its rules. Besides the real-time visual output, the future iterations of the installation will present the anonymously stored logs.
KRISTINA TICA. HUMAN OVERS[A]IGHT: THE OPS ROOM. 2025.COMPUTER VISION TEST OUTPUTS [SALIENCY MAP]. CODE BY LUKAS BIBL, IMAGE BY KRISTINA TICA
GitHub author: Lukas Bibl