Search

EP-4445348-B1 - SYSTEM AND METHOD FOR WITNESS REPORT ASSISTANT

EP4445348B1EP 4445348 B1EP4445348 B1EP 4445348B1EP-4445348-B1

Inventors

  • SIM, MOH LIM
  • KOH, Ling Hock
  • ASRI, Nur Diyana Mohd
  • LEE, Chun Hock
  • THAM, MUN YEW

Dates

Publication Date
20260506
Application Date
20221129

Claims (7)

  1. A computer-implemented method (500) comprising: capturing (505), with at least one camera, at least one image of an incident scene, wherein the incident scene is a location of an incident; receiving (510), from a witness to the incident, a verbal description of the incident, wherein the verbal description of the incident includes a generic reference to an element of the incident scene, wherein the generic reference to the element of the incident scene includes a hand gesture from the witness indicating the element of the scene (515) or detection of a keyword in the verbal description of the incident from the witness (525); transcribing (535) the verbal description of the incident scene to create a textual transcript; identifying (540) the element of the incident scene within the at least one image of the incident scene; determining (545) a specific identifier associated with the element of the incident scene, wherein the specific identifier identifies the element referred to by the generic reference with more specificity; and supplementing (565) the textual transcript of the description with the specific identifier.
  2. The method (500) of claim 1 wherein the generic reference to the element of the incident scene includes a hand gesture from the witness indicating at least one of a direction of motion and an initial and terminal location (520).
  3. The method (500) of claim 1 further comprising: altering (530) a field of view of the at least one camera based on the verbal description of the incident received from the witness when the generic reference is not viewable in an initial field of view of the at least one camera.
  4. The method (500) of claim 1 wherein identifying the specific identifier associated with the element of the incident scene further comprises: determining (550) a context of the incident; and identifying the specific identifier that is consistent with the context of the incident.
  5. The method (500) of claim 4 wherein determining the context of the incident further comprises: receiving (555) contextual information from descriptions of the incident provided by at least one other witness.
  6. A system comprising: a processor (610); and a memory (620) coupled to the processor (610), the memory (620) containing a set of instructions thereon that when executed by the processor (610) cause the processor (610) to perform the method (500) of any of the claims 1-5.
  7. A non-transitory processor readable medium (630) containing a set of instructions thereon that when executed by a processor (610) cause the processor (610) to perform the method (500) of any of the claims 1-5.

Description

BACKGROUND One of the tasks of public safety first responders that are responding to a public safety incident may be to gather information about the incident. Information can include biologic forensic information, such as fingerprints or DNA samples. Information can be other physical evidence, such as bullet casings, road measurements in the case of a traffic incident, pictures of the incident scene, etc. One particularly valuable form of evidence may be statements made by people who have witnessed the incident. For example, in the case of a car accident, a person who witnessed the accident may provide a statement that includes what the person saw. Although a public safety responder may transcribe a witness statement manually (e.g. with paper and pen, by typing into a computer, etc.) such a manual process may be inconvenient and/or inefficient. To alleviate this problem, often times a witness statement may be recorded. By recording the witness statement, the officer is freed from transcribing the witness statement and can instead focus on listening to what the witness is actually saying. In order to ensure that the witness statement is accurately captured in a textual report, the recorded witness statement may be automatically transcribed into text that can be included in the report. The transcription process may occur in real time, as the witness is making the statement, or it may occur offline, at a later time, by using the recording of the witness statement. Prior art document "A toolbox for the rapid prototyping of crime scene reconstructions in virtual reality" relates to use of virtual reality (VR) to replicate the crime scene. To perform a 3D reconstruction in VR, first the recorded data are prepared wherein all the data are converted to polygon meshes and cropped to the required area of interest to avoid data clutter and subsequent lagging in the VR visualization. The document presents a variety of tools which can be used in forensic investigations. Another prior art document "Applying virtual reality in forensics - a virtual scene walkthrough" relates to an approach for using forensic 3D data in conjunction with virtual reality to perform scene walkthroughs in the context of witness or suspect interrogations. These scene walkthroughs in VR can be reproduced and allow to see through the eyes of a witness by recording their behavior and actions. BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS In the accompanying figures similar or the same reference numerals may be repeated to indicate corresponding or analogous elements. These figures, together with the detailed description, below are incorporated in and form part of the specification and serve to further illustrate various embodiments of concepts that include the claimed invention, and to explain various principles and advantages of those embodiments FIG. 1 is an example of converting generic locations and action to specific names and actions, in accordance with the techniques described herein.FIG. 2 is an example of converting generic geographic landmarks to specific names and addresses, in accordance with the techniques described herein.FIG. 3 is an example of converting generic object identifiers to specific object identifiers, in accordance with the techniques described herein.FIG. 4 is an example of controlling Pan-Tilt-Zoom functions of a camera to capture images of an object, in accordance with the techniques described herein.FIG. 5 is an example flow diagram depicting the witness report assistant techniques described herein.FIG. 6 is an example device that implements the witness report assistant techniques described herein. Skilled artisans will appreciate that elements in the figures are illustrated for simplicity and clarity and have not necessarily been drawn to scale. For example, the dimensions of some of the elements in the figures may be exaggerated relative to other elements to help improve understanding of embodiments of the present disclosure. The apparatus and method components have been represented where appropriate by conventional symbols in the drawings, showing only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the disclosure with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein. DETAILED DESCRIPTION The ability to automatically and directly transcribe a witness statement into a report is a great aid to first responders. As mentioned above, the first responder can pay attention to what the witness is saying, rather than focusing on taking notes or typing what the witness says to manually transcribe the witness statement. Furthermore, machine transcription may aid in ensuring that the witness statement is correctly transcribed into the written report with less of a chance for error than with a human performing the transcription. Automatic transcription methods are continuous