AI system
- System
-
TrailGuard AI camera-alert system (embedded AI on an Intel computer-vision chip; cellular transmission)
- Application developer
-
Nightjar / RESOLVE, Washington DC (inventor Steve Gulick), with CVEDIA Ltd
- Configuration
-
Not assessed
- Workflow
-
Camouflaged camera units on trails inside the reserve used by both tigers and poachers. Cellular coverage allowing images to reach forest officials' phones in under a minute.
- Human oversight
-
Not assessed
- Relation to AI
-
The camera's on-board classifier filtered motion triggers to people and tigers and transmitted the poachers' images to officials' phones within about a minute. Identification and investigation were done by officials. The peer-reviewed account is co-authored by the developers (RESOLVE, CVEDIA) with Dudhwa and Wildlife Institute of India staff and stops at “investigating”. The arrest claim rests on a Clemson release quoting the ex-field director, developer press releases and The Hindu quoting the manufacturer and an unnamed participant.
- AI contribution
-
The camera's on-board classifier filtered motion triggers to people and tigers and transmitted the poachers' images to officials' phones within about a minute. Identification and investigation were done by officials. The peer-reviewed account is co-authored by the developers (RESOLVE, CVEDIA) with Dudhwa and Wildlife Institute of India staff and stops at “investigating”. The arrest claim rests on a Clemson release quoting the ex-field director, developer press releases and The Hindu quoting the manufacturer and an unnamed participant.
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
Dertien et al. (BioScience 2023): one TrailGuard AI unit captured poachers “carrying a gun and knives” on two dates and a poached chital; officials identified them. Arrests claimed only in releases.
- Category
-
Reduced Violence
- Beneficiary groups
-
Organizations. Society.
- Beneficiaries
-
Not assessed
- Distribution and access
-
Not assessed
- Costs and harms
-
Not assessed
Measurement
- Study design
-
Not assessed
- Setting and sample
-
Not assessed
- Comparison
-
Assumed alternative: camera traps without real-time notification
- Results
-
Assumed comparison. Reference: camera traps have lacked the real-time notification capabilities and practicality necessary for prevention of poaching. Result: notifications of tiger presence via email or push notification between 30 and 42 seconds after detections.
- Additional value from AI
-
Not assessed
- Denominators
-
Not assessed
- Materials for replication
-
Not assessed
Money
- Kind of value
-
Not assessed
- Currency and prices
-
Not assessed
- Period and unit
-
Not assessed
- Recipients and payers
-
Not assessed
- Gross or net
-
Not assessed
- Included costs
-
Not assessed
- Return and payback
-
Not assessed
People and places
- Participants
-
Developer: Nightjar / RESOLVE, Washington DC (inventor Steve Gulick), with CVEDIA Ltd. Operator: Dudhwa Tiger Reserve, Uttar Pradesh Forest Department, with the Global Tiger Forum, National Tiger Conservation Authority and Clemson University.
- Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
Officials act on the images while the poachers can still be found. The paper records identification and investigation only. The embedded classifier suppresses non-target triggers so that officials keep trusting the alerts.
- Replication attempts
-
1 follow-up entries. Benefit recurred: 1.
- Later findings
-
16 September 2023. Two days after the paper, The Hindu quoted Nightjar's Piyush Yadav that the Dudhwa poachers were arrested about a year after the images, with TrailGuard images playing a key role; Clemson's release of 15 September 2023 says the arrests came a few weeks later, and no forest department or court record was found.
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0318-source-0001–0006
- Citations
-
Numbered references below.
- Source relationships
-
Developer, Independent, Operator
- Original evidence
-
Not assessed
- Access and versions
-
Not assessed
- Supported findings
-
Not assessed
- Evidence links
-
Not assessed
- Evidence strength
-
Not assessed
- Missing evidence
-
Not assessed
Grades
- Assessed benefits
-
Organizations. Society.
- Depth
-
Organizations: 1. Society: Not assessed.
- Reasons
-
Organizations: Forest officials received the images in near real time and identified the individuals. The paper documents an investigation, not an arrest or prosecution, so the recorded gain is an investigative lead. Society: Protection of the reserve's wildlife from this gang is claimed through arrests only in the Clemson release, developer material and The Hindu's second-hand report. The paper notes a chital presumably poached before the second detection.
- Observed or intended
-
Not assessed
- Assessor and date
-
Not assessed
- Alternative assessments
-
Not assessed
- Fill
-
Independently reported
Entry details
- Related entries
-
Not assessed
- Field
-
Conservation / anti-poaching law enforcement. Anti-poaching enforcement.
- Purpose
-
Built to detect tigers and people on trails with embedded AI and send real-time images to forest officials. Detecting and transmitting the poachers' images was that purpose.
- Dates
-
Date basis unassessed: 2023 (precision unassessed). Updated: 21 October 2026.
- Version
-
SHA-256: 3da3ea7fd080…
References
- Other identifiers
-
Not assessed
- Category mappings
-
Not assessed
- Revisions
-
6 revisions. Latest: 21 October 2026.
Sources
-
Peer-reviewed study Developer
Dertien JS, Negi H, Dinerstein E, Krishnamurthy R, Negi HS, Gopal R, Gulick S, Pathak SK, Kapoor M, Yadav P, Benitez M, Ferreira M, Wijnveen AJ, Lee ATL, Wright B, Baldwin RF (2023). Mitigating human-wildlife conflict and monitoring endangered tigers using a real-time camera-based alert system. BioScience 73(10):748-757, doi:10.1093/biosci/biad076 (PMC10580963; authors include RESOLVE and CVEDIA developer staff and Dudhwa Tiger Reserve staff).
One unit within Kishanpur Wildlife Sanctuary captured a group of poachers carrying a gun and knives on two separate dates
Authorities were able to quickly identify the individuals via the transmitted images and were investigating the matter
-
News report Independent author
AFP (2023). AI of the tiger: Tiny camera 'protects' predator - and people. Taipei Times, 6 October 2023.
The research claims the cameras were immediately effective, picking up a tiger just 300 meters from a village, and on another occasion identifying a team of poachers.
-
News report Independent author
The Hindu (2023). AI cameras to curb poaching in Madhya Pradesh. 16 Sep 2023.
A year down, these poachers were arrested with images from TrailGuard playing a key role
-
News report Independent author
The Hindu (2023). Same article, lead paragraph.
caught poachers on camera that — a year down — helped forest authorities secure a conviction, according to a person involved in the experiment
-
Press release Deployer
Clemson News (2023). Clemson students' deployment of novel camera alert system, TrailGuard AI, featured in BioScience, promotes coexistence of tigers, humans. 15 September 2023 (university release of the lead author's institution; carries Nightjar/RESOLVE boilerplate; quotes former Dudhwa field director Sanjay Kumar Pathak).
TrailGuard AI offers park protection that led to the detection and arrest of poachers in Dudhwa,
Collections: Cross-border cases, Safeguards, Security and threat-watching.