Abstract
To address the issue of low depth estimation accuracy in complex goji berry orchards, this paper proposes a method for identifying and locating goji berries that combines the YOLO-VitBiS object detection network with stereo vision technology. Based on the YOLO11n backbone network, the C3K2 module in the backbone is first improved using the AdditiveBlock module to enhance its detail-capturing capability in complex environments. The AdditiveBlock introduces lightweight long-range interactions via residual additive operations, thereby strengthening global context modeling without significantly increasing computation. Subsequently, a weighted bidirectional feature pyramid network is introduced into the Neck to enable more flexible and efficient feature fusion. Finally, a lightweight shared detail-enhanced detection head is proposed to further reduce the network’s computational complexity and parameter count. The enhanced model is integrated with binocular stereo vision technology, employing the CREStereo depth estimation algorithm for disparity calculation during binocular stereo matching to derive the three-dimensional spatial coordinates of the goji berry target. This approach enables efficient and precise positioning. Experimental results demonstrate that the YOLO-VitBiS model achieves a detection accuracy of 96.6%, with a model size of 4.3MB and only 1.856M parameters. Compared to the traditional SGBM method and other deep learning approaches such as UniMatch, the CREStereo algorithm generates superior depth maps under complex conditions. Within a distance range of 400 mm to 1000 mm, the average relative error between the estimated and actual depth measurements is 2.42%, meeting the detection and ranging accuracy requirements for field operations and providing reliable recognition and localization support for subsequent goji berry harvesting robots.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 7
Claim · model-written summary
YOLO-VitBiS detected goji berries with 96.6% accuracy.
- Taxon
- Goji Berries
Lycium barbarumt0 - Outcome
- detection accuracye0
- Value
- 96.6%e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“the YOLO-VitBiS model achieves a detection accuracy of 96.6%”
t0“Goji Berries”
Claim · model-written summary
The detection model size was 4.3MB.
- Taxon
- Goji BerriesLycium barbarumt0
- Outcome
- model sizee0
- Value
- 4.3MBe0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“with a model size of 4.3MB”
t0“Goji Berries”
Claim · model-written summary
The detection model used 1.856M parameters.
- Taxon
- Goji BerriesLycium barbarumt0
- Outcome
- parameterse0
- Value
- 1.856Me0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“only 1.856M parameters”
t0“Goji Berries”
Claim · model-written summary
CREStereo produced superior depth maps to SGBM under complex conditions.
- Taxon
- Goji BerriesLycium barbarumt0
- Outcome
- depth mapse0
- Direction
- superiore0
- Qualifier
- complex conditionse0
- Comparator
- traditional SGBM methode0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Compared to the traditional SGBM method and other deep learning approaches such as UniMatch, the CREStereo algorithm generates superior depth maps under complex conditions”
t0“Goji Berries”
Claim · model-written summary
CREStereo produced superior depth maps to UniMatch under complex conditions.
- Taxon
- Goji BerriesLycium barbarumt0
- Outcome
- depth mapse0
- Direction
- superiore0
- Qualifier
- complex conditionse0
- Comparator
- UniMatche0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Compared to the traditional SGBM method and other deep learning approaches such as UniMatch, the CREStereo algorithm generates superior depth maps under complex conditions”
t0“Goji Berries”
Claim · model-written summary
Estimated depth had 2.42% mean relative error from 400 to 1000 mm.
- Taxon
- Goji BerriesLycium barbarumt0
- Outcome
- average relative errore0
- Value
- 2.42%e0
- Qualifier
- 400 mm to 1000 mme0
- Comparator
- actual depth measurementse0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Within a distance range of 400 mm to 1000 mm, the average relative error between the estimated and actual depth measurements is 2.42%”
t0“Goji Berries”
Claim · model-written summary
The authors judge detection and ranging accuracy sufficient for field operations.
- Taxon
- goji berryLycium barbarume0
- Outcome
- detection and ranging accuracy requirements for field operationse0
- Comparator
- requirements for field operationse0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“meeting the detection and ranging accuracy requirements for field operations and providing reliable recognition and localization support for subsequent goji berry harvesting robots”