.png){kind=icon}
.png){kind=icon}
Return
Exploiting Partial JPEG Decoding to Mitigate On-Device Image Processing
.png){kind=icon}
PRE
AI
K
H
高
X
W
W
DOI：10.1109/tmc.2026.3697605.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Device-cloud collaborative inference is often necessary for resource-constrained IoT devices that cannot support full on-device models. To minimize bandwidth and support concurrency, existing methods typically compress images before transmission. However, these approaches often ignore the significant overhead of decoding native JPEG camera output, especially for high-resolution frames. Our measurements show that the on-device (Raspberry Pi 4B) decoding overhead for 700 KB JPEG format is <inline-formula><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula>14.4x the latency of on-cloud (GeForce RTX 3090) meter recognition inference. To reduce on-device decoding overhead, we design DC Camera, which is built upon a JPEG camera and leverages partial JPEG decoding to efficiently extract DC features from high-resolution images, significantly mitigating on-device image processing overhead. These DC features can preserve structural information better than conventional downsampled images. We utilize DC Camera to implement fast meter recognition system and deploy the system in material science laboratory to monitor multiple meters. Our evaluation demonstrates that compared to state-of-the-art (SOTA) methods, DC Camera can reduce on-device computation overhead by <inline-formula><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula>5.8x and decrease transmission volume by <inline-formula><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula>90.9x, without inference accuracy degradation.
Keywords:
JPEG decoding
direct current
device-cloud collaborative inference
Journal
IF:
9.2
Papers:
5.6K
Citations:
1.8W
Organization
Cited Papers