CucumberVision at the Edge: Accuracy, Throughput, and Energy of RGB-D Cucumber S
Overview
This research evaluates a non-contact fruit sizing pipeline using RGB-D imagery for cucumber length measurement on low-power single-board computers (NVIDIA Jetson Orin Nano and Raspberry Pi 4) compared to an RTX 3050 Ti workstation. The study demonstrates that sub-centimetre accuracy (mean absolute error of 0.58 cm) is preserved across platforms when using TensorRT FP16 compilation on the Jetson. Key findings include detection latency of 72 ms per fruit at 0.84 cm accuracy, energy consumption of 42.2 J per fruit on the Jetson, and structural failure of whole-graph INT8 quantization requiring exclusion of the detection head to restore function. The paper defines an accuracy-throughput-energy envelope with three non-dominated configurations and provides rules for selecting hardware based on specific operational constraints.
Generated from attributed reports · Updated 2 days ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · energy_per_fruit: 42.2 other · Basis not reported
“h INT8 quantization of the NMS-free detection head fails structurally, returning no detections, because one output tensor carries both pixel coordinates and confidences; we show that no calibration strategy can avoid this. Excluding the head restores function at 1.37x. Energy per fruit is 42.2 J on the Jetson, and its 7 W mode consumes 73% more than its 15 W mode. The Raspberry Pi with MobileSAM costs 2.5x more per f”
Exact source · revision 1Source owner not reported
Reported quantity · detection_latency_084cm: 72 other · Basis not reported
“rRT FP16 compilation cuts Jetson detection latency 2.57x, giving two operating points on one board: 72 ms per fruit at 0.84 cm, or 2.74 s at 0.64 cm. Four ablations map the design space. For prompted segmentation backends, measurement accuracy is fixed by the backend and reproduces across platforms to within 0.01 cm, while its cost is fixed by the platform and varies 214x, so the two choices are separable. Whole-grap”
Exact source · revision 1Source owner not reported
Reported quantity · detection_latency_064cm: 2.74 other · Basis not reported
“rRT FP16 compilation cuts Jetson detection latency 2.57x, giving two operating points on one board: 72 ms per fruit at 0.84 cm, or 2.74 s at 0.64 cm. Four ablations map the design space. For prompted segmentation backends, measurement accuracy is fixed by the backend and reproduces across platforms to within 0.01 cm, while its cost is fixed by the platform and varies 214x, so the two choices are separable. Whole-grap”
Exact source · revision 1Source owner not reported
Reported quantity · mean_absolute_error: 0.58 other · Basis not reported
“c spline estimator) on an NVIDIA Jetson Orin Nano and a Raspberry Pi 4, and characterize both against an RTX 3050 Ti workstation by replaying 50 identical greenhouse captures of 7 specimens, with specimen-level cluster-bootstrap statistics. Accuracy is preserved: mean absolute error (MAE) is 0.58 cm (95% CI 0.46-0.69) on both the workstation and the Jetson at matched precision, with a paired difference of zero. Tenso”
Exact source · revision 1Source owner not reported
Reported quantity · jetson_power_7w_mode: 7 other · Basis not reported
“h INT8 quantization of the NMS-free detection head fails structurally, returning no detections, because one output tensor carries both pixel coordinates and confidences; we show that no calibration strategy can avoid this. Excluding the head restores function at 1.37x. Energy per fruit is 42.2 J on the Jetson, and its 7 W mode consumes 73% more than its 15 W mode. The Raspberry Pi with MobileSAM costs 2.5x more per f”
Exact source · revision 1Source owner not reported
Reported quantity · jetson_power_15w_mode: 15 other · Basis not reported
“h INT8 quantization of the NMS-free detection head fails structurally, returning no detections, because one output tensor carries both pixel coordinates and confidences; we show that no calibration strategy can avoid this. Excluding the head restores function at 1.37x. Energy per fruit is 42.2 J on the Jetson, and its 7 W mode consumes 73% more than its 15 W mode. The Raspberry Pi with MobileSAM costs 2.5x more per f”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalCucumberVision at the Edge: Accuracy, Throughput, and Energy of RGB-D Cucumber Sizing on Jetson Orin Nano and Raspberry Pi 4
This research evaluates a non-contact fruit sizing pipeline using RGB-D imagery for cucumber length measurement on low-power single-board computers (NVIDIA Jetson Orin Nano and Raspberry Pi 4) compared to an RTX 3050 Ti workstation. The study demonstrates that sub-centimetre accuracy (mean absolute error of 0.58 cm) is preserved across platforms when using TensorRT FP16 compilation on the Jetson. Key findings include detection latency of 72 ms per fruit at 0.84 cm accuracy, energy consumption of 42.2 J per fruit on the Jetson, and structural failure of whole-graph INT8 quantization requiring exclusion of the detection head to restore function. The paper defines an accuracy-throughput-energy envelope with three non-dominated configurations and provides rules for selecting hardware based on specific operational constraints.
Event coverage history
Current attention 3·Peak within the comparable range 4（2026-11-10 11:00 UTC）·Change within the comparable range over 24 hours –
The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).