Skeptics and believers alike agree on one thing: if paranormal investigation is to be taken seriously, it needs rigorous methodology and verifiable technology. Enter the SLS camera, a tool that applies real computer vision science to the search for the unknown.
This article dives into the actual technology behind SLS cameras, how ML Kit skeleton tracking works, and why this represents a genuine advancement in paranormal research methodology.
What Is SLS Technology?
SLS (Stick Lens System) technology originated in the gaming industry with Microsoft's Kinect sensor. The principle is straightforward: project an infrared grid into the environment, measure how the grid distorts against surfaces, and use that depth data to identify human-shaped forms.
What made SLS revolutionary for paranormal investigation was its ability to detect human forms independently of visible light conditions. In complete darkness, the infrared projection still produces a depth map, and the skeleton tracking algorithms still work.
Google ML Kit Pose Detection: The Engine Behind NOCTEM
Modern SLS camera apps like NOCTEM use Google Mobile Vision's ML Kit for pose detection. Here's how it works:
- Input: The camera feed is processed frame by frame.
- Detection: ML Kit's pose detection model analyzes each frame for human anatomical structures.
- Key Points: When detected, 33 skeletal key points are identified, from head and shoulders to fingertips and ankles.
- Overlay: These points are connected to form a stick figure skeleton overlay on the camera feed.
Technical Detail: ML Kit's pose detection model was trained on millions of images of humans in various poses, lighting conditions, and environments. It doesn't just detect full bodies, it can identify partial skeletons when only parts of a form are visible, which is particularly relevant in paranormal contexts where entities may be partially manifested.
Why This Matters for Paranormal Research
The key advantage of ML-based SLS detection over human observation is objectivity. A human investigator might miss a subtle form in the darkness, or might see something that isn't there (pareidolia). An ML model applies the same detection criteria consistently to every frame, eliminating subjective interpretation at the capture stage.
Limitations and How Responsible Investigators Address Them
No technology is perfect, and honest paranormal research requires acknowledging limitations:
- False positives: Objects with human-like shapes can trigger detection. Mitigation: environmental control, clear the area of furniture and objects before SLS scanning.
- Training bias: The ML model was trained on living humans, not paranormal entities. Mitigation: cross-reference SLS captures with EVP recordings and other sensor data.
- Interpretation: The skeleton overlay is an interpretation, not direct evidence of an entity. Mitigation: always present raw camera footage alongside SLS overlay for context.
The Future of AI in Paranormal Investigation
As machine learning models become more sophisticated, their application in paranormal research will only grow. We're already seeing ML applied to EVP analysis, anomaly detection in environmental sensor data, and pattern recognition across large evidence databases.
NOCTEM represents the current state of the art, bringing professional-grade ML-powered investigation tools to mobile devices at an accessible one-time price.
Experience the Science of Paranormal Investigation
Download NOCTEM and access professional ML Kit SLS camera technology, high-fidelity EVP recording, and complete investigation tools. $14.99 one-time. No subscriptions.
🔬 Get NOCTEM on Google Play
Discussion & Comments
Tried this practice? Tell us what happened below. Reader results are the most useful feedback we get — they show other practitioners what to expect and tell us which guides to write next.