You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The two moving figures you're seeing are simulated people from the server's built-in simulation mode — they are not real detections. The sensing server renders them by default when it hasn't confirmed reliable live CSI data.
Quick check: curl http://localhost:3000/health — look at the "source" field. If it says "simulated", the server is not using your ESP32 data yet.
Common causes when Docker is involved:
The ESP32's --target-ip must be your host machine's LAN IP, not 127.0.0.1 or the Docker container IP.
@xiaofuchen, have you made any progress so far? I’m not sure whether using only one eps-s3 can provide sufficient information for reliable inference.
Also, from my perspective, this project is highly data-driven, meaning that different building maps may require customized inference parameters to achieve stable performance.
Multi-person slot count — partitions the top-K subcarriers into top_k / 2 groups (clamped to [1, EDGE_MAX_PERSONS]), computes per-group filtered breathing/heart-rate estimates, and reports the slot count as pkt.n_persons. This is a slot-capacity heuristic, not a learned counter — the reported count tracks subcarrier diversity, not actual occupancy.
This was a firmware bug, not your setup — the people-count was a placeholder that ignored presence, so it always showed a fixed number (you saw 2) regardless of how many people were actually there. Root cause + fix in #892, which gates the count on actual presence so an empty room reports 0. Full root-cause analysis: #803.
Activity
fox007ggr commentedon May 1, 2026
你好,你是怎么安装的,我在ubuntu 22.4 上面使用 docker pull ruvnet/wifi-densepose:latest 他总是报错,能帮助下吗
failed to do request: Get "https://registry-1.docker.io/v2/ruvnet/wifi-densepose/referrers/sha256:cdfe2915bbf00efb306653c4c4895059756a3a593312f158d8b5a81c38a5d61c": dial tcp 199.59.149.201:443: i/o timeout
ruvnet commentedon May 7, 2026
The two moving figures you're seeing are simulated people from the server's built-in simulation mode — they are not real detections. The sensing server renders them by default when it hasn't confirmed reliable live CSI data.
Quick check:
curl http://localhost:3000/health— look at the"source"field. If it says"simulated", the server is not using your ESP32 data yet.Common causes when Docker is involved:
--target-ipmust be your host machine's LAN IP, not127.0.0.1or the Docker container IP.--network host(Linux only).--source esp32when starting the sensing server.See #301 for the full troubleshooting guide (Simulation vs Live and Docker sections).
Generated by Claude Code
xiaofuchen commentedon May 8, 2026
{
"clients": 1,
"source": "esp32",
"status": "ok",
"tick": 277
}
我已经全链路检查过的了,不是模拟的模式,就是真实的csi数据,但这个数据波动很大,如图是房间没人的情况下的数据。而且在房间没人和有人的情况下,数据都一直变化很大,是什么因素影响了?还是这个esp32-s3的板子的csi数据本身就不对?我现在只想实现最简单的存在检测和人数统计,目前看这个情况,是没有达到这个效果。
AkonLau commentedon May 14, 2026
@xiaofuchen, have you made any progress so far? I’m not sure whether using only one eps-s3 can provide sufficient information for reliable inference.
Also, from my perspective, this project is highly data-driven, meaning that different building maps may require customized inference parameters to achieve stable performance.
xiaofuchen commentedon May 14, 2026
@AkonLau 不,我试过任何方式了,都不能实现。我也去查看源码了,这个项目只是一个随机数,根本没有实现功能。
ruvnet commentedon May 17, 2026
你好 @xiaofuchen — 谢谢报告。"客厅里只有1个人但UI显示2个人在动" 是一个已知的限制,不是配置错误。原因和解决方向如下。
为什么会显示多个"人"
固件目前的 "person count" 不是真正的人数识别器,而是一个 subcarrier slot heuristic:
(摘自
firmware/esp32-csi-node/README.md,这段说明是为了回应类似的反馈 — PR #573 / 关联 issue #568 才更新的。)简单说:当一个人在房间里走动时,会扰动多个 subcarrier — 多个 subcarrier 被分组后,UI 看到的
n_persons就可能是 2、3 等。现在能做的(无需改代码)
presence_threshold会自适应)。如果在有人的状态下启动,误检率会高很多。subk_count(top-K 数量):n_persons,代价是失去一些多人区分能力。n_persons只是 slot 计数。正在路上的真正修复
RollingP95自适应归一化 +dedup_factor运行时 API,正是为了解决 "同一个人被多个节点重复计数" 这个问题。这个 PR 在等贡献者 rebase 到 main(我已经留言)。merge 之后默认情况会大幅好转。.rvf模型文件时,跑的是 signal-based heuristic 而不是真正的 17-keypoint pose inference。这也是 "实际 1 人但显示 2 个 stick figure" 的另一个原因。热力图 (heatmap) 路径
热力图需要 multistatic fusion (3+ 节点 + 知道每个节点的物理位置)。当前 sensing-server 已经支持,但需要:
--source esp32 --node-positions positions.json(位置文件给每个node_id一个[x, y, z])signal_field(20×20 网格)如果你的客厅只用了 1-2 个节点,热力图功能会被 disable。
下一步建议:先用上面的"重新校准"+
--subk-count 4试试,看 motion 数值能不能稳定下来。如果还是 noisy,等 #491 merge 之后再升级。Pose 那条线要等 #509 的模型权重发布。如果有具体的日志/截图能帮诊断,贴在这里我可以帮看。
Merge #491: feat(sensing-server): adaptive person count — RollingP95 …
ruvnet commentedon May 19, 2026
更新 — PR #491 已合并到 main (通过集成 PR #633)。这个 PR 直接修复了 "客厅里只有1个人但 UI 显示 2 个人在动" 这个问题。
原理: 之前 server 使用固定的归一化分母 (
variance/300,motion_band_power/250,spectral_power/500),当你的 ESP32 实测值超过这些限制时,归一化输入会饱和到 1.0,动态范围收缩,导致单个人被聚类成 2+ 个 subcarrier group。新版本用
RollingP95自校准 (600 sample / ~30 秒滑动窗口) — 部署 30 秒后会自动校准到你的具体环境,不需要再调--subk-count。等下一个 server 镜像发布后 (
ruvnet/wifi-densepose:latestDocker 镜像) 拉新版本,应该会自动好转。或者如果你从源码编译,pull main 重新cargo run -p wifi-densepose-sensing-server --release。如果在新版本下还是有问题,请贴一下:
curl http://localhost:3000/api/v1/nodes输出motion_energy和n_persons数值感谢报告 — 这个 bug 是 multi-node 部署的一个常见痛点,#491 是直接的修复。
ruvnet commentedon May 19, 2026
关闭 — 修复已合并到 main,通过 PR #491 (集成自 #633)。
修复内容: 用
RollingP95自校准归一化替换之前固定的归一化分母 (variance/300/motion_band_power/250/spectral_power/500)。这些固定分母是"客厅 1 个人但 UI 显示 2 个人"问题的根本原因 — 当实测值超过限制时归一化输入会饱和到 1.0,导致单人被聚类成 2+ 个 subcarrier group。等下一个 server 镜像发布后 (
ruvnet/wifi-densepose:latestDocker 镜像) 拉新版本,部署 30 秒后会自动校准到你的环境,不需要再调--subk-count。冷启动 (<60 samples) 仍然使用旧的固定分母作为安全后备,30 秒滑动窗口填满后新算法接管。
如果新版本下还是有问题,请 reopen 并贴:
curl http://localhost:3000/api/v1/nodes输出motion_energy和n_personsRUST_LOG=info)感谢报告 — 这是 multi-node 部署常见痛点的根因分析推动 #491 优先合并的关键。
fix(edge): gate multi-person activation on presence — stop reporting …
markt-heximal commentedon Jun 1, 2026
This was a firmware bug, not your setup — the people-count was a placeholder that ignored presence, so it always showed a fixed number (you saw 2) regardless of how many people were actually there. Root cause + fix in #892, which gates the count on actual presence so an empty room reports 0. Full root-cause analysis: #803.
这是固件的问题,不是你的配置:人数显示是一个占位实现,没有结合"是否有人"(presence)的判断,所以即使客厅里只有你一个人,也会显示固定的人数。根因与修复见 #892 —— 让人数随实际存在状态变化(空房间显示 0)。详细分析见 #803。
Merge ruvnet#491: feat(sensing-server): adaptive person count — Rolli…