Files

virgil a601a5cbc1 feat: sensecap watcher add inference (#1312 )

* feat: Wake up when a person is detected

* fix: Solve the problem of no sound when using WakeWordInvoke

* fix: Solve the problem of triggering dialogue when the person has not left

* feat(vision): 优化视觉检测逻辑并增加配置接口

本次提交旨在优化视觉检测功能,使其行为更自然、更智能,并为用户提供灵活的配置选项。

主要更新包括:

1. 引入了更精细的检测状态机:

   - IDLE: 空闲状态,等待检测目标。

   - VALIDATING: 验证状态,在检测到目标后,持续一段时间(可配置)以确认其存在,防止误触发。

   - COOLDOWN: 冷却状态,在一次成功交互后进入,避免过于频繁的打扰。

2. 新增了用于配置视觉检测的 MCP 工具:

   - self.vision.get_detection_config: 获取当前的检测参数(阈值、冷却间隔、验证时长、目标类型)。

   - self.vision.set_detection_config: 允许用户动态修改这些参数,以适应不同场景。

3. 性能优化:

   - 增加了配置参数的内存缓存,避免了在检测循环中对 NVS 的频繁访问。

* feat: Inference using Model 4

* feat: default inference disable

* feat: version cmd change to output json

* fix: fix image display

* Fix include directives for esp_check and esp_app_desc

---------

Co-authored-by: Spencer <love4yzp@gmail.com>
Co-authored-by: Xiaoxia <terrence@tenclass.com>

2025-10-20 21:18:44 +08:00

config_en.json

Switch to 2.0 branch (#1152 )

2025-09-04 15:41:28 +08:00

config.h

Feat sscma camera (#770 )

2025-06-06 14:22:39 +08:00

config.json

Switch to 2.0 branch (#1152 )

2025-09-04 15:41:28 +08:00

README_en.md

Switch to 2.0 branch (#1152 )

2025-09-04 15:41:28 +08:00

README.md

Switch to 2.0 branch (#1152 )

2025-09-04 15:41:28 +08:00

sensecap_audio_codec.cc

将项目版本更新至1.5.9，优化内存使用，增加主任务栈大小至8192，优化固件升级流程，重构主循环为MainEventLoop，添加新版本检查功能，更新音频编解码器的DMA配置常量。

2025-04-13 11:47:15 +08:00

sensecap_audio_codec.h

Add SenseCAP Watcher (#241 )

2025-03-04 20:38:53 +08:00

sensecap_watcher.cc

feat: sensecap watcher add inference (#1312 )

2025-10-20 21:18:44 +08:00

sscma_camera.cc

feat: sensecap watcher add inference (#1312 )

2025-10-20 21:18:44 +08:00

sscma_camera.h

feat: sensecap watcher add inference (#1312 )

2025-10-20 21:18:44 +08:00

README_en.md

Build Instructions

One-click Build

python scripts/release.py sensecap-watcher -c config_en.json

Manual Configuration and Build

idf.py set-target esp32s3

Configuration

idf.py menuconfig

Select the board:

Xiaozhi Assistant -> Board Type -> SenseCAP Watcher

There are some additional configuration options for the watcher. Please select them in menuconfig:

CONFIG_BOARD_TYPE_SENSECAP_WATCHER=y
CONFIG_ESPTOOLPY_FLASHSIZE_32MB=y
CONFIG_PARTITION_TABLE_CUSTOM_FILENAME="partitions/v2/32m.csv"
CONFIG_BOOTLOADER_CACHE_32BIT_ADDR_QUAD_FLASH=y
CONFIG_ESPTOOLPY_FLASH_MODE_AUTO_DETECT=n
CONFIG_IDF_EXPERIMENTAL_FEATURES=y
CONFIG_LANGUAGE_EN_US=y
CONFIG_SR_WN_WN9_JARVIS_TTS=y

Build and Flash

idf.py -DBOARD_NAME=sensecap-watcher-en build flash

Note: If your device was previously shipped with the SenseCAP firmware (not the Xiaozhi version), please be very careful with the flash partition addresses to avoid accidentally erasing the device information (such as EUI) of the SenseCAP Watcher. Otherwise, even if you restore the SenseCAP firmware, the device may not be able to connect to the SenseCraft server correctly! Therefore, before flashing the firmware, be sure to record the necessary device information to ensure you have a way to recover it!

You can use the following command to back up the factory information:

# Firstly backup the factory information partition which contains the credentials for connecting the SenseCraft server
esptool.py --chip esp32s3 --baud 2000000 --before default_reset --after hard_reset --no-stub read_flash 0x9000 204800 nvsfactory.bin